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

    Neuronpedia

    INDEX
    Explanations

    references to internal processes or components

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

    "internal" and related terms

    np_acts-logits-general · gemini-2.0-flash

    internal operations and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rophoresis
    -0.60
    yntaxException
    -0.57
     getRule
    -0.56
    KommentareTeilen
    -0.56
     onPostExecute
    -0.53
     gages
    -0.53
     OFDb
    -0.52
     psycopg
    -0.52
     EconPapers
    -0.52
    msgTypes
    -0.52
    POSITIVE LOGITS
     internal
    2.41
    internal
    2.31
    Internal
    2.27
     Internal
    2.20
     INTERNAL
    2.00
    INTERNAL
    1.97
     internally
    1.95
     interno
    1.48
     internes
    1.48
     external
    1.45
    Act Density 0.110%

    No Known Activations