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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    BL
    0.78
    .
    0.73
    ings
    0.73
    IT
    0.72
    ML
    0.64
    DE
    0.64
    BER
    0.64
    र
    0.64
    수
    0.64
    AD
    0.63
    POSITIVE LOGITS
    :
    0.81
    {
    0.80
    ные
    0.80
    ين
    0.77
    im
    0.77
    i
    0.75
    an
    0.72
    <0xBB>
    0.72
    га
    0.71
    ي
    0.71
    Act Density 0.000%

    No Known Activations