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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     user
    -0.08
     eu
    -0.07
    (_
    -0.07
    .commands
    -0.07
    front
    -0.07
    cré
    -0.06
    /custom
    -0.06
     undo
    -0.06
    _User
    -0.06
    本地
    -0.06
    POSITIVE LOGITS
    멧
    0.07
    ｗ
    0.07
     Cron
    0.07
    삼
    0.07
     nargin
    0.07
     toolbox
    0.07
     prohibition
    0.07
    .pad
    0.07
     glamour
    0.07
    很满意
    0.06
    Act Density 0.045%

    No Known Activations