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

    Neuronpedia

    INDEX
    Explanations

    requests and obligations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'ye
    -0.07
    endereco
    -0.07
    URA
    -0.06
    检测
    -0.06
     ممکن
    -0.06
     thank
    -0.06
     activists
    -0.06
     Tiles
    -0.06
     carn
    -0.06
     UNIVERS
    -0.06
    POSITIVE LOGITS
    .gson
    0.07
    инок
    0.07
    =_('
    0.07
    yıl
    0.06
    [b
    0.06
     firearm
    0.06
    pg
    0.06
    [(
    0.06
     "..
    0.06
    _AF
    0.06
    Act Density 0.184%

    No Known Activations