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

    Neuronpedia

    INDEX
    Explanations

    gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CSR
    -0.07
    ive
    -0.07
     Reliable
    -0.07
    -dat
    -0.06
    太多的
    -0.06
    илось
    -0.06
    .of
    -0.06
    ặp
    -0.06
     dressed
    -0.06
    elcome
    -0.06
    POSITIVE LOGITS
    协办
    0.08
     CONVERT
    0.07
    研究成果
    0.07
    ᾦ
    0.07
    -prom
    0.07
     editing
    0.07
     indifference
    0.07
     launching
    0.07
    -self
    0.06
    VIEW
    0.06
    Act Density 0.033%

    No Known Activations