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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     berita
    0.79
     acara
    0.77
    plein
    0.73
     Messages
    0.73
    BTC
    0.71
     Bahan
    0.71
    awatan
    0.68
     İlk
    0.68
     Wię
    0.67
    şık
    0.66
    POSITIVE LOGITS
    라는
    0.77
    粲
    0.73
    అ
    0.73
    된
    0.70
    ერ
    0.68
    ouncy
    0.67
    0.66
    어
    0.64
    дання
    0.64
    ೆಯ
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.