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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    微软雅黑
    -0.06
     SOUTH
    -0.06
    .access
    -0.06
    =msg
    -0.06
     Fits
    -0.06
    .middle
    -0.06
    (strip
    -0.06
    ORG
    -0.06
    loaded
    -0.06
     外
    -0.06
    POSITIVE LOGITS
     flurry
    0.07
     few
    0.07
     psychiatrist
    0.06
     Unt
    0.06
     Kosovo
    0.06
     Andr
    0.06
     #-}↵
    0.06
     تنظيف
    0.06
     холод
    0.06
    ๑
    0.06
    Act Density 0.016%

    No Known Activations