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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unscathed
    0.72
     étn
    0.72
    年以上
    0.71
     žena
    0.71
    wale
    0.71
     Manche
    0.70
    a
    0.70
    COUNT
    0.69
    aar
    0.69
     कड़ी
    0.69
    POSITIVE LOGITS
     kill
    0.69
    那时候
    0.69
    ultats
    0.66
    ごろ
    0.66
     impl
    0.65
    ocarbon
    0.65
    Þ
    0.65
    飲食
    0.64
     efectos
    0.64
     respuestas
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.