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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    means
    -0.07
     skip
    -0.07
     france
    -0.07
    人文
    -0.07
     ד
    -0.07
    前列腺
    -0.07
     arte
    -0.07
    腧
    -0.07
    严重
    -0.07
     sass
    -0.06
    POSITIVE LOGITS
     Bonnie
    0.08
     самых
    0.08
     ואת
    0.07
     ומה
    0.07
     Rally
    0.07
    amente
    0.07
     ?>><?
    0.07
    _PA
    0.07
     umbrella
    0.07
    .Hour
    0.07
    Act Density 0.149%

    No Known Activations