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

    Neuronpedia

    INDEX
    Explanations

    the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     গুণে
    1.27
     laminar
    1.05
    radian
    1.05
    喿
    1.04
     phonon
    1.02
     guesswork
    1.02
    ições
    1.02
     চাহি
    0.99
     linal
    0.96
    ртом
    0.96
    POSITIVE LOGITS
    ภัย
    1.18
    an
    1.13
     similaire
    1.10
    ಕ
    1.09
    这款
    1.05
    没有
    1.04
    峡
    1.04
    esteem
    1.03
    ك
    1.03
    ల
    1.03
    Act Density 0.125%

    No Known Activations