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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dimerization
    1.54
    𝗶
    1.35
     billowing
    1.33
    ینگ
    1.31
     pakas
    1.30
    ्य
    1.30
    TextBlock
    1.29
    inator
    1.28
     buzzer
    1.28
     landet
    1.28
    POSITIVE LOGITS
    $-
    1.17
    $.}
    1.06
    앙
    1.03
     собой
    0.98
    $.
    0.93
     боль
    0.92
    على
    0.90
    ffiti
    0.89
     astr
    0.88
     различными
    0.87
    Act Density 0.000%

    No Known Activations