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

    Neuronpedia

    INDEX
    Explanations

    ethnicity and race

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.74
    '
    0.71
    nish
    0.63
     गया
    0.62
     entren
    0.60
    Nav
    0.60
    Session
    0.60
    Ne
    0.58
    SO
    0.58
    Cho
    0.58
    POSITIVE LOGITS
    ز
    0.84
    и
    0.74
    ə
    0.72
    м
    0.71
    ir
    0.70
    ו
    0.70
    ه
    0.69
    ны
    0.68
     ethnicity
    0.66
    ж
    0.66
    Act Density 0.002%

    No Known Activations