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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     BY
    0.81
     ¿
    0.77
    Variety
    0.76
    Terms
    0.73
    :”
    0.71
    FirstName
    0.71
    Percentages
    0.71
    Quand
    0.70
    liegen
    0.70
    ューズ
    0.70
    POSITIVE LOGITS
     eddies
    1.15
    ным
    1.09
    ্মান
    1.06
     autocratic
    1.05
    はもちろん
    1.04
    ды
    1.03
    fection
    0.99
    وون
    0.99
    ю
    0.96
     effluents
    0.95
    Act Density 0.001%

    No Known Activations