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

    Neuronpedia

    INDEX
    Explanations

    overtime hours and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    1.00
    et
    0.92
    ’
    0.84
    ના
    0.82
     of
    0.76
    '
    0.73
     for
    0.72
    in
    0.69
    d
    0.69
    eline
    0.68
    POSITIVE LOGITS
    ق
    1.01
    рма
    0.87
     overtime
    0.83
    да
    0.82
    트를
    0.75
    加班
    0.73
     arrivée
    0.72
     примере
    0.71
    이가
    0.71
    น
    0.71
    Act Density 0.001%

    No Known Activations