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

    Neuronpedia

    INDEX
    Explanations

    each/every day/week/month/year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yearly
    0.45
    Annual
    0.44
    hourly
    0.44
    annual
    0.43
    Hourly
    0.42
     yıllık
    0.42
     Days
    0.41
    ম্ত
    0.41
     hourly
    0.41
    Days
    0.41
    POSITIVE LOGITS
     night
    0.58
     day
    0.54
     week
    0.54
     year
    0.53
     month
    0.52
     couple
    0.51
     few
    0.50
     vez
    0.46
     φορά
    0.46
     paar
    0.46
    Act Density 0.025%

    No Known Activations