Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    announcements and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     centuries
    1.05
     século
    0.96
     bohemian
    0.94
     enfermos
    0.93
     Pythagoras
    0.92
     Pythagorean
    0.92
     துன்ப
    0.92
     siglos
    0.89
    overty
    0.89
     pottery
    0.88
    POSITIVE LOGITS
     출시
    1.78
     announced
    1.70
    アップデート
    1.60
     Updates
    1.53
     updates
    1.52
     versions
    1.51
     announcement
    1.50
     Announced
    1.50
     released
    1.50
     rebranded
    1.49
    Act Density 3.905%

    No Known Activations