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

    Neuronpedia

    INDEX
    Explanations

    women's roles and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.51
     UILabel
    0.51
    ternal
    0.50
    ('#
    0.49
    iding
    0.49
    "/
    0.48
    '/
    0.47
    ٹا
    0.47
    /"+
    0.47
     เศ
    0.47
    POSITIVE LOGITS
     mostly
    0.48
    USU
    0.43
    incare
    0.42
     chỉ
    0.41
    mostly
    0.41
    Anh
    0.41
    LAR
    0.41
    Phr
    0.40
     बचें
    0.40
    प्रकाश
    0.40
    Act Density 0.002%

    No Known Activations