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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     geöffnet
    0.82
    keit
    0.77
    ണ്ടും
    0.77
    ционное
    0.74
     echter
    0.74
     nors
    0.73
    тной
    0.73
    ębior
    0.73
     Donner
    0.72
    ilm
    0.71
    POSITIVE LOGITS
    ה
    0.84
     он
    0.83
     proves
    0.81
     is
    0.74
     يت
    0.73
    ことになる
    0.73
    𝑠
    0.73
     இந்த
    0.73
    А
    0.73
     バ
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.