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

    Neuronpedia

    INDEX
    Explanations

    power dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DAY
    0.65
    cen
    0.62
     Day
    0.60
    day
    0.59
    getDay
    0.58
    リング
    0.58
    Day
    0.58
    ussians
    0.57
    ناو
    0.57
    火车
    0.56
    POSITIVE LOGITS
     па
    0.76
    スパ
    0.70
    パ
    0.69
     pa
    0.69
     sprout
    0.68
    PA
    0.67
    epa
    0.67
     Па
    0.66
    pars
    0.66
    pac
    0.66
    Act Density 0.199%

    No Known Activations