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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .
    1.09
    ی
    0.78
    ר
    0.69
    ist
    0.67
    at
    0.59
    ן
    0.59
    '
    0.58
    4
    0.56
    ine
    0.56
     que
    0.55
    POSITIVE LOGITS
    诙
    0.60
    oplane
    0.58
    汅
    0.58
    ном
    0.57
     Rajiv
    0.57
    urally
    0.56
     Buick
    0.56
     andRow
    0.56
    куляр
    0.56
    藠
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.