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

    Neuronpedia

    INDEX
    Explanations

    months and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     использовать
    0.43
    स्यों
    0.43
    ༤
    0.43
     увеличения
    0.41
     ৮০
    0.40
    ཋ
    0.40
    𝔀
    0.39
     pluripotent
    0.39
     sarcom
    0.38
     USSR
    0.38
    POSITIVE LOGITS
     June
    1.09
     September
    1.09
     April
    1.05
     October
    1.04
     November
    1.02
     July
    0.99
     August
    0.97
     February
    0.97
    September
    0.96
     March
    0.95
    Act Density 0.013%

    No Known Activations