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

    Neuronpedia

    INDEX
    Explanations

    references to historical or political events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    time or location

    np_acts-logits-general · gemini-2.0-flash

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSlice
    -0.85
     tomorrow
    -0.84
    MLLoader
    -0.73
     tonight
    -0.71
     مشين
    -0.70
    ParallelGroup
    -0.70
    明日
    -0.69
    rungsseite
    -0.68
     NSCoder
    -0.67
    Vendredi
    -0.66
    POSITIVE LOGITS
     בשנת
    1.55
     vuonna
    1.43
     năm
    1.21
     عام
    1.19
     tahun
    1.09
     سنة
    1.05
     years
    1.01
     années
    1.00
     roku
    0.97
     leta
    0.97
    Act Density 1.099%

    No Known Activations