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

    Neuronpedia

    INDEX
    Explanations

    adults

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ー
    1.06
    or
    1.01
    цион
    1.01
    κής
    0.98
     %\
    0.96
    hidupan
    0.95
    蓣
    0.94
     catalyze
    0.93
    楂
    0.93
    yx
    0.93
    POSITIVE LOGITS
    要想
    1.01
    ל
    1.00
     volition
    0.97
     methionine
    0.96
     оку
    0.96
    ु
    0.96
    buscador
    0.95
    lihat
    0.94
     दाखिल
    0.94
     годов
    0.94
    Act Density 0.056%

    No Known Activations