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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     thúc
    0.82
    מר
    0.81
    and
    0.80
     compassionate
    0.78
     narrowly
    0.78
     bóng
    0.75
     Borussia
    0.75
     jargon
    0.72
     Bóng
    0.72
     réunion
    0.71
    POSITIVE LOGITS
     efectivamente
    0.69
    t
    0.68
     নিশ্চয়
    0.67
    kannya
    0.67
     sobres
    0.67
    К
    0.66
     سبب
    0.66
    k
    0.66
    kiego
    0.66
    ture
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.