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

    Neuronpedia

    INDEX
    Explanations

    administrative, secretarial work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EXPECTED
    -0.08
    破
    -0.07
     Pist
    -0.07
     Specification
    -0.07
     bif
    -0.07
    .Popen
    -0.07
     sku
    -0.07
    .Authorization
    -0.07
    ��
    -0.07
    nect
    -0.06
    POSITIVE LOGITS
     female
    0.07
     म
    0.07
    ᄋ
    0.07
    ǀ
    0.07
    Woman
    0.06
    问卷
    0.06
     היא
    0.06
    年の
    0.06
     הד
    0.06
    ведите
    0.06
    Act Density 0.014%

    No Known Activations