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

    Neuronpedia

    INDEX
    Explanations

    named / called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     высокие
    0.48
    xcscheme
    0.47
     njega
    0.44
    ᐱ
    0.44
     якія
    0.43
    MPs
    0.42
     kuiten
    0.42
    ‌آ
    0.40
    iejęt
    0.40
    バイス
    0.39
    POSITIVE LOGITS
    名叫
    0.79
     denominada
    0.77
     bernama
    0.73
    叫做
    0.70
    名为
    0.70
     denominado
    0.69
     chamada
    0.69
     namens
    0.68
     called
    0.67
     llamada
    0.67
    Act Density 0.026%

    No Known Activations