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

    Neuronpedia

    INDEX
    Explanations

    foreign language signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tecnica
    0.48
     utilize
    0.44
     shave
    0.43
    Mutex
    0.42
     madde
    0.41
     ایسے
    0.41
     legalize
    0.40
     fale
    0.40
     #
    0.40
     jezika
    0.40
    POSITIVE LOGITS
    ang
    0.63
    ge
    0.45
    ί
    0.45
    ча
    0.44
    inderung
    0.44
    ㅃ
    0.43
    ခြ
    0.43
    bedarf
    0.43
     واس
    0.42
    ЕНИ
    0.42
    Act Density 0.011%

    No Known Activations