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

    Neuronpedia

    INDEX
    Explanations

    Ends with "ules"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﾇ
    -0.09
    ய
    -0.07
    新政
    -0.07
     señor
    -0.07
    掞
    -0.07
    Ô
    -0.07
     cul
    -0.07
    AndPassword
    -0.06
    僖
    -0.06
    通知书
    -0.06
    POSITIVE LOGITS
    Score
    0.08
     ago
    0.07
    _cart
    0.07
    IndexChanged
    0.07
    /docker
    0.07
    (score
    0.06
    饮用
    0.06
     An
    0.06
     homemade
    0.06
     klub
    0.06
    Act Density 0.000%

    No Known Activations