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

    Neuronpedia

    INDEX
    Explanations

    terms related to abstract and theoretical discussions

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

    beliefs, ideologies, principles, or party proposals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.90
    parsedMessage
    -0.83
    DeleteBehavior
    -0.79
    jsonwebtoken
    -0.75
     '\\;'
    -0.75
    RenderAtEndOf
    -0.73
     fashiola
    -0.73
     müſſen
    -0.72
    OGND
    -0.72
     AssemblyCulture
    -0.72
    POSITIVE LOGITS
     principles
    0.39
     principle
    0.31
     wereld
    0.31
     principe
    0.30
     tenets
    0.29
    tama
    0.28
     emphasis
    0.27
     ideology
    0.26
     vyb
    0.26
     Principles
    0.26
    Act Density 0.047%

    No Known Activations