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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﺩ
    0.98
    ﺭ
    0.87
     второй
    0.78
    7
    0.77
    ﺴ
    0.77
    8
    0.76
    सा
    0.75
     некоторых
    0.74
    ‘
    0.74
     вось
    0.73
    POSITIVE LOGITS
     lark
    0.67
     lucrat
    0.66
    harga
    0.65
    ighthouse
    0.64
     signific
    0.63
     roya
    0.62
    ंदरे
    0.62
    emaster
    0.62
    ernen
    0.61
    🥇
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.