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

    Neuronpedia

    INDEX
    Explanations

    growth and adoption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    1.23
    ك
    1.05
    وم
    0.96
    ৫
    0.93
    го
    0.93
    的价格
    0.91
    ومي
    0.89
    话
    0.88
    Ꮙ
    0.88
    azione
    0.88
    POSITIVE LOGITS
    ر
    1.52
    و
    1.39
     buds
    1.14
    ل
    1.13
    _
    1.10
     kasv
    1.09
     by
    1.08
     рам
    1.07
     and
    1.05
     Grow
    1.04
    Act Density 0.077%

    No Known Activations