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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mannit
    0.82
    irit
    0.81
     pontos
    0.79
     iba
    0.78
     곱
    0.78
     vão
    0.78
     обы
    0.76
    lk
    0.75
     ea
    0.75
    ны
    0.75
    POSITIVE LOGITS
    NewUrlParser
    0.73
    禊
    0.72
     tariff
    0.71
    ㊗
    0.71
     செய்யப்பட்டு
    0.71
    ுள்ளார்
    0.70
     நூற்றாண்டில்
    0.70
    出版
    0.69
    TacToe
    0.68
     publishes
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.