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

    Neuronpedia

    INDEX
    Explanations

    Code related to data arrays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    十分
    -0.07
    properties
    -0.07
     indulge
    -0.07
    的优点
    -0.07
     dois
    -0.06
    -Smith
    -0.06
     afs
    -0.06
    塆
    -0.06
    ㈫
    -0.06
    忽悠
    -0.06
    POSITIVE LOGITS
    它们
    0.08
    ucing
    0.07
    ,top
    0.07
    涯
    0.07
    PARAM
    0.07
    _PIX
    0.07
     Jam
    0.07
    Nr
    0.07
     yourselves
    0.07
     towns
    0.07
    Act Density 0.048%

    No Known Activations