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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    da
    0.82
    Все
    0.80
    ual
    0.79
    4
    0.79
     Slightly
    0.76
    Pues
    0.75
    ADMIN
    0.74
    pada
    0.73
    na
    0.73
    ac
    0.72
    POSITIVE LOGITS
    ா
    1.06
    ੀ
    0.88
     بندی
    0.88
    ары
    0.86
    تبر
    0.84
     weir
    0.83
    рый
    0.82
    рные
    0.82
     продукты
    0.82
    рное
    0.82
    Act Density 0.000%

    No Known Activations