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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rane
    -0.07
     STUD
    -0.06
     являются
    -0.06
     Hel
    -0.06
    戏
    -0.06
     incluso
    -0.06
    混合
    -0.06
     alınan
    -0.06
    GIN
    -0.06
     enlight
    -0.06
    POSITIVE LOGITS
     письмен
    0.07
     lh
    0.06
    ª
    0.06
    -down
    0.06
     pozit
    0.06
    CCR
    0.06
     ترجم
    0.06
    _public
    0.06
    intersect
    0.06
    蛋
    0.06
    Act Density 0.179%

    No Known Activations