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

    Neuronpedia

    INDEX
    Explanations

    amount of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ुक्त
    0.47
    烁
    0.46
     Bağ
    0.46
    اران
    0.45
    fono
    0.44
    метров
    0.44
    encerramento
    0.44
    carbox
    0.44
    啶
    0.44
    पेपर
    0.44
    POSITIVE LOGITS
     of
    0.58
    t
    0.56
     amount
    0.56
    j
    0.55
    v
    0.52
     AMOUNT
    0.49
    Amount
    0.48
     Amounts
    0.47
     Amount
    0.47
    el
    0.46
    Act Density 0.017%

    No Known Activations