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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     втор
    0.82
     epile
    0.79
     exib
    0.79
     pode
    0.78
     tém
    0.77
     معی
    0.77
     embeds
    0.76
     trasm
    0.76
    邪魔
    0.75
    s
    0.75
    POSITIVE LOGITS
     roadside
    0.68
    iin
    0.68
     congregate
    0.68
    Przeczytaj
    0.67
     tireless
    0.67
     Jeder
    0.66
     Aku
    0.66
     coniferous
    0.66
     faculty
    0.66
    উট
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.