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

    Neuronpedia

    INDEX
    Explanations

    references to months and their corresponding abbreviations

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

    months of the year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.36
    IsMutable
    -0.35
    Empereur
    -0.31
    Rüyada
    -0.31
     toepassing
    -0.31
     problemu
    -0.31
     amarilla
    -0.30
    tahankan
    -0.30
     AssemblyCulture
    -0.29
     vPvB
    -0.28
    POSITIVE LOGITS
     February
    0.93
     October
    0.91
     December
    0.90
     September
    0.89
     July
    0.88
    October
    0.88
     March
    0.87
    February
    0.87
     April
    0.86
     August
    0.85
    Act Density 0.028%

    No Known Activations