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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ne
    0.95
    t
    0.94
     Tr
    0.86
    na
    0.84
    e
    0.82
    a
    0.82
    r
    0.82
     A
    0.81
    chutz
    0.80
    re
    0.80
    POSITIVE LOGITS
    ات
    0.83
    Workbook
    0.70
    setChecked
    0.69
    ្នាំ
    0.68
    CharSequence
    0.68
     идут
    0.66
    山上
    0.66
     امتحان
    0.65
    Cuánt
    0.64
    Predictions
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.