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

    Neuronpedia

    INDEX
    Explanations

    female/male

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    強
    -0.07
    .getExternal
    -0.07
     Sorting
    -0.07
    Customer
    -0.07
     Bang
    -0.07
     represented
    -0.06
     addTo
    -0.06
     sorting
    -0.06
    fdb
    -0.06
    від
    -0.06
    POSITIVE LOGITS
     Male
    0.06
    ecess
    0.06
     mini
    0.06
     Hiç
    0.06
    ousedown
    0.06
    шки
    0.06
    女子
    0.06
     fict
    0.06
    Ş
    0.06
    ategorical
    0.06
    Act Density 0.003%

    No Known Activations