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

    Neuronpedia

    INDEX
    Explanations

    objective, stationary, input, outside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seguinte
    0.88
    शीलता
    0.83
     Yatha
    0.79
    زي
    0.78
    ﻰ
    0.76
     vời
    0.75
     طويل
    0.75
    蛄
    0.74
     Sebelumnya
    0.74
     dugo
    0.73
    POSITIVE LOGITS
    s
    0.86
    та
    0.79
     zatem
    0.73
    お客様
    0.65
    cale
    0.64
    טו
    0.64
     ס
    0.63
     UPC
    0.63
    https
    0.62
    ку
    0.62
    Act Density 0.001%

    No Known Activations