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

    Neuronpedia

    INDEX
    Explanations

    math/statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    党员干部
    -0.07
     Только
    -0.07
    餐饮
    -0.07
    ircular
    -0.07
    辅导员
    -0.07
    תו
    -0.07
    ublished
    -0.06
     sufficient
    -0.06
    섭
    -0.06
     zusammen
    -0.06
    POSITIVE LOGITS
    iques
    0.07
    \Helpers
    0.07
    OCKET
    0.07
    centroid
    0.07
    𝙜
    0.07
     molding
    0.06
     Crate
    0.06
    getParameter
    0.06
    logy
    0.06
    <Edge
    0.06
    Act Density 0.043%

    No Known Activations