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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ي
    0.69
    मध्ये
    0.64
    جين
    0.64
    ين
    0.63
    ב
    0.59
    ó
    0.58
    áč
    0.58
    তা
    0.57
    人
    0.57
    नी
    0.57
    POSITIVE LOGITS
    _
    0.91
     innovative
    0.61
    ;
    0.60
    {
    0.58
     for
    0.55
    .
    0.54
    <
    0.52
    amate
    0.51
    ac
    0.49
     an
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.