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

    Neuronpedia

    INDEX
    Explanations

    Statement class and debugger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ет
    1.55
    ativos
    1.48
    ির
    1.41
     bestimmt
    1.41
    คุณ
    1.36
    样的
    1.34
    ною
    1.30
    heet
    1.28
    やつ
    1.28
     sores
    1.27
    POSITIVE LOGITS
    ოლოდ
    1.66
    ק
    1.64
     probablement
    1.60
    neſs
    1.59
     påver
    1.56
     എന്നാല്‍
    1.54
     Еще
    1.50
     jaką
    1.49
    ة
    1.49
     kesin
    1.38
    Act Density 0.000%

    No Known Activations