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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     andrew
    0.77
    emper
    0.75
    ادت
    0.71
    يل
    0.71
    ascii
    0.69
    ahm
    0.69
    ادم
    0.69
    َاب
    0.68
    ologist
    0.68
     subalgebra
    0.67
    POSITIVE LOGITS
    ר
    0.82
    সামরিক
    0.79
    λιο
    0.78
     ve
    0.77
    ุปกรณ์
    0.76
    是一家
    0.75
    worldly
    0.73
    Transaksi
    0.72
     מט
    0.71
     때
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.