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

    Neuronpedia

    INDEX
    Explanations

    elements related to media types and their associated formats in code

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

    Preceding tokens before periods or brackets

    np_acts-logits-general · gemini-2.0-flash

    Java builder pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.56
    はじめに
    -0.55
    orsese
    -0.52
    windowFixed
    -0.49
    enterOuterAlt
    -0.47
    multer
    -0.44
    toyage
    -0.44
    jsonwebtoken
    -0.44
    ніципа
    -0.43
    ตร์
    -0.43
    POSITIVE LOGITS
    builder
    0.69
    values
    0.68
    RequestBuilder
    0.68
    Builder
    0.60
     ；
    0.56
     Builder
    0.56
    builders
    0.56
     Values
    0.56
    Values
    0.55
     values
    0.54
    Act Density 0.195%

    No Known Activations