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

    Neuronpedia

    INDEX
    Explanations

    current

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GMT
    -0.07
    \Image
    -0.07
     tf
    -0.07
     speeding
    -0.07
    [↵
    -0.07
     ==↵
    -0.07
    ＂
    -0.07
    各省
    -0.07
    隐藏
    -0.07
    对付
    -0.07
    POSITIVE LOGITS
     recher
    0.07
    .notice
    0.06
     fst
    0.06
    _Off
    0.06
    -bg
    0.06
     Workbook
    0.06
    İK
    0.06
    kır
    0.06
    .hits
    0.06
    clusão
    0.06
    Act Density 0.012%

    No Known Activations