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

    Neuronpedia

    INDEX
    Explanations

    references to parsing functions and processes within code snippets

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

    code parser operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toMatchSnapshot
    -0.52
    -0.49
    WriteLiteral
    -0.47
    <![
    -0.45
    arschu
    -0.43
    GEBURTS
    -0.42
    Glide
    -0.42
    StructEnd
    -0.42
    LookAnd
    -0.41
    GrantedAuthority
    -0.39
    POSITIVE LOGITS
    parser
    3.38
     parser
    2.20
    Parser
    1.95
     Parser
    1.80
    PARSER
    1.71
    parsers
    1.43
     PARSER
    1.34
     parsing
    1.20
    parsing
    1.15
     Parsing
    1.15
    Act Density 0.004%

    No Known Activations