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

    Neuronpedia

    INDEX
    Explanations

    man/woman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.73
    IntoConstraints
    -0.71
    ValueStyle
    -0.68
     kaarangay
    -0.66
     typelib
    -0.64
     disambiguazione
    -0.64
     arşivlendi
    -0.64
    InSection
    -0.60
    transQ
    -0.59
     Exacts
    -0.58
    POSITIVE LOGITS
    hwa
    0.61
    ’
    0.54
     bernama
    0.52
     named
    0.51
     who
    0.50
    '
    0.49
     насељу
    0.48
    devamını
    0.47
    راسیون
    0.46
    ised
    0.45
    Act Density 0.007%

    No Known Activations