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

    Neuronpedia

    INDEX
    Explanations

    model, formula, section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     debris
    0.42
     dun
    0.41
     autof
    0.40
     medical
    0.39
     prescriptions
    0.38
    debris
    0.38
     automobiles
    0.36
     caravan
    0.36
     taus
    0.36
     নেতৃ
    0.36
    POSITIVE LOGITS
     модели
    0.42
    諏
    0.42
    逮捕
    0.41
    踵
    0.40
     डेवलपमेंट
    0.40
    чью
    0.39
     ठीक
    0.38
    モデル
    0.38
     прока
    0.38
    模型的
    0.38
    Act Density 0.000%

    No Known Activations