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

    Neuronpedia

    INDEX
    Explanations

    work hours and shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Silber
    0.41
     icon
    0.38
     peptide
    0.37
    langle
    0.36
     발견
    0.35
    ไปยัง
    0.35
     Proc
    0.35
     syntax
    0.35
    ických
    0.35
    周围
    0.35
    POSITIVE LOGITS
     hours
    1.38
    hours
    1.23
     Hours
    1.16
     근무
    1.13
     ساعات
    1.12
    Hours
    1.11
     overtime
    1.09
     shift
    1.06
     workday
    1.05
     HOURS
    1.04
    Act Density 0.026%

    No Known Activations