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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nad
    0.78
     Transl
    0.71
    Sw
    0.69
    ột
    0.68
    Exper
    0.67
    N
    0.66
     Sh
    0.66
     Học
    0.66
    wach
    0.66
    wak
    0.66
    POSITIVE LOGITS
    轵
    0.84
    istir
    0.74
     linal
    0.74
     syarat
    0.72
    ことは
    0.71
     codewords
    0.71
    ಗ್ಗೆ
    0.70
    らしい
    0.69
     शिक्षकों
    0.69
     retard
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.