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

    Neuronpedia

    INDEX
    Explanations

    separators and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    巧
    -0.08
    然而
    -0.07
    久
    -0.07
     uphill
    -0.07
    擊
    -0.07
     rocky
    -0.07
    -eff
    -0.07
    igitte
    -0.07
    未知
    -0.07
    然
    -0.07
    POSITIVE LOGITS
     ಪತ್ರ
    0.10
     पत्र
    0.09
     планы
    0.09
     विवरण
    0.09
     отзывы
    0.09
    README
    0.08
     ත
    0.08
     تعريف
    0.08
     بأي
    0.08
     testimon
    0.08
    Act Density 0.032%

    No Known Activations