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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical references or citations in the text

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

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.57
    AndEndTag
    -0.54
    TagMode
    -0.51
     createSprite
    -0.47
    WriteTagHelper
    -0.47
    はじめに
    -0.45
    InjectAttribute
    -0.43
     contextLoads
    -0.43
    GTCX
    -0.41
    -0.41
    POSITIVE LOGITS
    semb
    0.47
     بیشتری
    0.45
     AssemblyCompany
    0.44
     referenties
    0.42
     Wikimedijinoj
    0.41
    ########.
    0.40
     vre
    0.37
    humanité
    0.36
     Four
    0.36
     Fat
    0.36
    Act Density 0.133%

    No Known Activations