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

    Neuronpedia

    INDEX
    Explanations

    pass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    膈
    -0.08
     IsNot
    -0.08
    aths
    -0.08
    يين
    -0.07
    理性
    -0.07
    主公
    -0.07
    DER
    -0.07
     alguien
    -0.07
    🙅
    -0.07
    being
    -0.06
    POSITIVE LOGITS
    taxonomy
    0.07
    𑘁
    0.07
    Dup
    0.07
    .ResultSet
    0.07
    PictureBox
    0.07
    个赛季
    0.07
     bandwidth
    0.07
     concatenate
    0.07
    净利润
    0.06
     payroll
    0.06
    Act Density 0.011%

    No Known Activations