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

    Neuronpedia

    INDEX
    Explanations

    oper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arguments
    -0.08
    .name
    -0.07
    〜
    -0.07
    _ZONE
    -0.07
    statement
    -0.07
     motif
    -0.07
    培训
    -0.07
    XYZ
    -0.07
    France
    -0.07
    广州
    -0.07
    POSITIVE LOGITS
    IColor
    0.08
    庤
    0.08
    鳍
    0.07
    文化传媒
    0.07
     NBA
    0.07
    (cuda
    0.07
    гер
    0.06
    LATED
    0.06
    _pe
    0.06
     porno
    0.06
    Act Density 0.009%

    No Known Activations