Add final social demo post link
Browse files
README.md
CHANGED
|
@@ -16,6 +16,12 @@ short_description: Live EEG for base vs abliterated Gemma
|
|
| 16 |
|
| 17 |
The goal is not to claim that language models literally feel human emotions. Instead, Activation Brain visualizes stable emotion-like hidden-state regimes and translates them into more model-native signals such as valence, activation, uncertainty, constraint, conflict, and warmth.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## Models
|
| 20 |
|
| 21 |
- **`google/gemma-4-12B-it`** — base instruction model
|
|
|
|
| 16 |
|
| 17 |
The goal is not to claim that language models literally feel human emotions. Instead, Activation Brain visualizes stable emotion-like hidden-state regimes and translates them into more model-native signals such as valence, activation, uncertainty, constraint, conflict, and warmth.
|
| 18 |
|
| 19 |
+
|
| 20 |
+
## Demo and Social Post
|
| 21 |
+
|
| 22 |
+
- **Social post / demo video:** https://x.com/2reb_fl/status/2066586581587136681
|
| 23 |
+
- **Direct demo URL:** https://build-small-hackathon-activation-brain.hf.space/?cb=v19layout
|
| 24 |
+
|
| 25 |
## Models
|
| 26 |
|
| 27 |
- **`google/gemma-4-12B-it`** — base instruction model
|