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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    dades
    1.12
    drawable
    1.11
    lllll
    1.11
     शख
    1.10
    handlebars
    1.10
    multiply
    1.08
    issima
    1.07
    lions
    1.07
    settings
    1.06
    VIDED
    1.06
    POSITIVE LOGITS
    ^{
    1.09
    ために
    1.07
     linseed
    1.05
    ר
    1.03
    ਈ
    1.00
    ẩn
    0.99
     elastomer
    0.98
     привіт
    0.97
    رى
    0.97
     スト
    0.94
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.