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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax elements or components from programming languages

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

    stateChanged()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.63
     CURIAM
    -0.56
    findpost
    -0.55
    UnusedPrivate
    -0.55
     Wikiseite
    -0.54
     navideño
    -0.53
     useAppContext
    -0.53
     Réponses
    -0.52
     CreateTagHelper
    -0.51
    moveToFirst
    -0.50
    POSITIVE LOGITS
     Morm
    0.42
    lobby
    0.42
     lobby
    0.40
     Moul
    0.37
     bruges
    0.36
     Mor
    0.36
    DllImport
    0.36
    遣
    0.36
    ilities
    0.35
     entre
    0.35
    Act Density 0.001%

    No Known Activations