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

    Neuronpedia

    INDEX
    Explanations

    instruction, input, response, search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     וש
    1.31
    ות
    1.20
     역할
    1.20
    ного
    1.17
     やっ
    1.16
     kuna
    1.06
     ค
    1.04
     Thế
    1.03
     принципе
    1.03
    anie
    1.02
    POSITIVE LOGITS
    ا
    1.16
    ‌ای
    1.11
    ເວລາ
    1.11
     souhaitez
    1.09
    ي
    1.09
    тные
    1.08
    y
    1.05
    க்கோ
    1.05
    彡
    1.05
    NCIA
    1.04
    Act Density 0.001%

    No Known Activations