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

    Neuronpedia

    INDEX
    Explanations

    conditions or requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.09
    .↵
    -0.08
    ”.
    -0.07
    identified
    -0.07
    ’.
    -0.07
    。
    -0.07
    ै?↵
    -0.07
    =>"
    -0.06
     منابع
    -0.06
    ...)↵↵
    -0.06
    POSITIVE LOGITS
    سو
    0.06
    哥
    0.06
     sworn
    0.06
    fang
    0.06
     satın
    0.06
     {%
    0.06
    니까
    0.06
    phot
    0.06
    حل
    0.06
    폭
    0.06
    Act Density 5.265%

    No Known Activations