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

    Neuronpedia

    INDEX
    Explanations

    work shifts and schedules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    0.72
    ad
    0.60
    ."),
    0.58
    Advice
    0.58
    Complaint
    0.57
     t
    0.56
    <0x0D>
    0.56
    '),
    0.56
    advice
    0.56
    .")
    0.55
    POSITIVE LOGITS
     работать
    0.68
     Revolución
    0.67
     ساعات
    0.67
     ночь
    0.66
    shifts
    0.65
     ദിവസം
    0.64
     nuit
    0.64
     heures
    0.63
     Trabajo
    0.63
    hiyam
    0.63
    Act Density 0.015%

    No Known Activations