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

    Neuronpedia

    INDEX
    Explanations

    rotation, sigmoid, activation functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iniciativas
    0.68
     नियोक्ता
    0.66
     spiritual
    0.65
     humanitarian
    0.64
     boreal
    0.64
     seasonal
    0.63
     zahl
    0.63
     oportunidades
    0.63
     kív
    0.63
     disponibilité
    0.63
    POSITIVE LOGITS
     Angle
    0.76
    を使って
    0.70
    矩阵
    0.70
    を用いて
    0.70
     performs
    0.67
     introduces
    0.67
     नामक
    0.66
     फर्जी
    0.66
    耦合
    0.65
    دست
    0.65
    Act Density 0.000%

    No Known Activations