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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ida
    -0.07
    文化
    -0.07
    苦
    -0.07
    균
    -0.07
    َة
    -0.07
     Mirror
    -0.07
    OSE
    -0.07
    верж
    -0.07
     BJ
    -0.06
    平均
    -0.06
    POSITIVE LOGITS
     제목
    0.07
    .astype
    0.06
     Abbott
    0.06
    =cut
    0.06
    .Other
    0.06
    .docker
    0.06
    News
    0.06
     revoke
    0.06
     extrapol
    0.06
    oba
    0.06
    Act Density 0.122%

    No Known Activations