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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ль
    0.98
    nements
    0.88
    ña
    0.84
    л
    0.84
    ्ञ
    0.82
    zione
    0.82
     misdemeanor
    0.82
    onan
    0.81
    т
    0.80
    zes
    0.77
    POSITIVE LOGITS
    Disclaimer
    0.92
    Из
    0.86
    Arrows
    0.86
    তারা
    0.83
    Rating
    0.82
    Same
    0.82
     ै
    0.82
    SAME
    0.82
    কাতার
    0.81
     ясно
    0.81
    Act Density 0.002%

    No Known Activations