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

    Neuronpedia

    INDEX
    Explanations

    Cannot post new topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FETCH
    -0.07
    睾
    -0.07
    (Control
    -0.07
    Exercise
    -0.07
    _NUM
    -0.06
     />↵↵
    -0.06
     brides
    -0.06
     gulp
    -0.06
    人生
    -0.06
    (ur
    -0.06
    POSITIVE LOGITS
     pobl
    0.07
    مكاف
    0.07
    🥁
    0.06
     потреб
    0.06
    ⌯
    0.06
    ColorBrush
    0.06
    拥堵
    0.06
    友善
    0.06
    求职
    0.06
    0.06
    Act Density 0.000%

    No Known Activations