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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kurang
    0.83
    长安
    0.82
     sorprendente
    0.82
    ဵ
    0.81
    损伤
    0.78
    ighthouse
    0.78
     sial
    0.78
    ற்கு
    0.77
     Toms
    0.77
    itabbo
    0.77
    POSITIVE LOGITS
    I
    0.95
    П
    0.92
    ни
    0.89
    AA
    0.79
    A
    0.77
    な
    0.72
    Б
    0.67
    ?
    0.66
    О
    0.66
    И
    0.66
    Act Density 0.000%

    No Known Activations