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

    Neuronpedia

    INDEX
    Explanations

    share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imm
    -0.07
    icket
    -0.07
     in
    -0.07
    بع
    -0.06
    篱
    -0.06
    Norm
    -0.06
    _cov
    -0.06
     trou
    -0.06
    Csv
    -0.06
     atol
    -0.06
    POSITIVE LOGITS
     -------↵
    0.07
    tório
    0.07
    랍
    0.07
     ----------↵
    0.07
    ⠀
    0.06
    信息公开
    0.06
    -------↵↵
    0.06
    ----------↵
    0.06
    -account
    0.06
    巴士
    0.06
    Act Density 0.000%

    No Known Activations