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

    Neuronpedia

    INDEX
    Explanations

    metals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provide
    -0.07
    agine
    -0.07
     wp
    -0.07
    可知
    -0.07
     realpath
    -0.07
     Hughes
    -0.07
     varargin
    -0.07
     precursor
    -0.07
    .AbsoluteConstraints
    -0.07
    時期
    -0.07
    POSITIVE LOGITS
    混
    0.08
    興
    0.07
     Truck
    0.07
     swearing
    0.06
    Ḟ
    0.06
    人大
    0.06
    imed
    0.06
    信
    0.06
    降低
    0.06
    𝗡
    0.06
    Act Density 0.016%

    No Known Activations