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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ando
    0.76
    ية
    0.68
    on
    0.67
    il
    0.63
    인
    0.62
    ine
    0.61
    يل
    0.60
     from
    0.58
    ند
    0.57
    able
    0.57
    POSITIVE LOGITS
     Wednesdays
    0.76
    CAUSE
    0.72
     Fridays
    0.66
     Mondays
    0.66
     Saturdays
    0.64
     Tuesdays
    0.62
     Thursdays
    0.61
    Weekly
    0.61
     weekly
    0.60
     Wochen
    0.60
    Act Density 0.005%

    No Known Activations