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

    Neuronpedia

    INDEX
    Explanations

    extend the season

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keh
    0.43
     Cupid
    0.42
     December
    0.41
     द्
    0.39
     November
    0.38
    icelli
    0.37
     RIN
    0.37
    柢
    0.37
     Rin
    0.36
     Wärme
    0.36
    POSITIVE LOGITS
     season
    1.94
    Season
    1.66
    season
    1.63
     시즌
    1.61
     сезона
    1.58
     сезоне
    1.58
     Season
    1.56
     seizoen
    1.53
     сезо
    1.52
     сезон
    1.51
    Act Density 0.012%

    No Known Activations