fix: add sdk: static + sync to latest org card content

README.md

@@ -1,7 +1,14 @@
 ---
 title: Divinci AI
+emoji: 🧠
+colorFrom: green
+colorTo: yellow
+sdk: static
+pinned: false
+short_description: Feature-level interpretability for open transformers
 ---
 
+
 # Divinci AI
 
 Feature-level interpretability artifacts for open transformers — built openly, validated empirically.
@@ -10,7 +17,6 @@ A **vindex** is a transformer's weights decompiled into a queryable feature data
 
 Think of it as the model's index: the thing you search before you run it.
 
----
 
 ## Interactive viewer
 
@@ -20,7 +26,6 @@ Think of it as the model's index: the thing you search before you run it.
 
 Pick any of 9 models from the dropdown. Toggle between the 3D cylinder spiral and a flat 2D circuit/network view. Hit **⇌ Compare** to render the current model alongside Bonsai 1-bit, side-by-side — the contrast between fp16 structure (organized rings) and 1-bit dissolution (scattered cloud) is the most direct picture of what 1-bit training does to a transformer's internal organization that we know how to render. Search for entity features (`?q=paris&model=gemma-4-e2b`) to see real probe-derived activations light up across the layer stack — backed by a 5000-token offline-built search index.
 
----
 
 ## Published vindexes
 
@@ -39,7 +44,6 @@ Cross-family evidence in hand: **Gemma**, **Qwen3**, **Mistral**, **Llama**, **O
 | **Bonsai 8B** | 1-bit (Qwen 3 base, post-quantized) | 8B | *vindex pending publish* | 0.429 | **C5 = 1** (circuit dissolved); var@64 = 0.093 |
 | **BitNet b1.58-2B-4T** | 1-bit (Microsoft, native) | 2B | *vindex pending publish* | (Phase 2 pending) | **var@64 = 0.111** mean across 30 layers — n=2 confirmation of dissolution |
 
----
 
 ## What's a vindex?
 
@@ -49,7 +53,6 @@ Concretely: given a query like `"Paris → capital"`, a vindex walk returns the
 
 LarQL (the toolchain that builds vindexes) is open-source: [github.com/chrishayuk/larql](https://github.com/chrishayuk/larql) | [github.com/Divinci-AI/larql](https://github.com/Divinci-AI/larql).
 
----
 
 ## Research
 
@@ -73,7 +76,6 @@ Mechanistic knowledge editing in transformer feature space. Includes a negative
 
 Working notebooks: [github.com/Divinci-AI/server/tree/preview/notebooks](https://github.com/Divinci-AI/server/tree/preview/notebooks)
 
----
 
 ## Working in public
 
@@ -81,6 +83,5 @@ Every measurement in our papers traces back to a notebook and a commit. Negative
 
 If you replicate a result and find a discrepancy, open an issue on the LarQL repo.
 
----
 
 *Vindexes on this org are free for academic and research use (CC-BY-NC 4.0). Commercial licensing: mike@divinci.ai*