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

    Neuronpedia

    INDEX
    Explanations

    references to financial information and economic implications

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

    Citation or reference formatting

    np_acts-logits-general · gemini-2.0-flash

    numbers and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tens
    -0.74
     Tens
    -0.74
    Tens
    -0.68
    Diwedd
    -0.65
    tens
    -0.63
     @}
    -0.61
     Piz
    -0.56
    cookieParser
    -0.56
    RAINT
    -0.55
    AndEndTag
    -0.54
    POSITIVE LOGITS
    Hentet
    0.62
    Rüyada
    0.58
    Jîn
    0.57
    GraphicsUnit
    0.56
    baga
    0.52
     Juga
    0.52
     iprot
    0.52
     TextInputType
    0.50
    erdings
    0.49
    lış
    0.49
    Act Density 0.192%

    No Known Activations