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

    Neuronpedia

    INDEX
    Explanations

    expressions of anticipation or surprise

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

    pause or interruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.42
    XmlAccessType
    -0.38
    HasAnnotation
    -0.36
     AE
    -0.35
     cherchés
    -0.33
    amsmath
    -0.33
    WriteAttribute
    -0.32
    клопе
    -0.32
     projec
    -0.31
    }{*}{}
    -0.31
    POSITIVE LOGITS
    fromnode
    0.51
    heça
    0.50
    webElementXpaths
    0.48
     Widerspruch
    0.46
     LOWER
    0.46
     normaux
    0.45
    domada
    0.45
     useAppContext
    0.45
     EconPapers
    0.45
    åringen
    0.44
    Act Density 0.017%

    No Known Activations