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

    Neuronpedia

    INDEX
    Explanations

    JSON-like structures or key-value pairs in a data format

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

    Text within curly braces

    np_acts-logits-general · gemini-2.0-flash

    structured data parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [
    -0.55
    ↵↵
    -0.53
     e
    -0.49
    ban
    -0.48
    .
    -0.48
    bb
    -0.48
    :
    -0.48
    fn
    -0.45
     f
    -0.45
     ma
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    1.47
    GEBURTSDATUM
    1.35
    ValueStyle
    1.27
    principalColumn
    1.21
    tagHelperRunner
    1.20
    MigrationBuilder
    1.14
    webElementXpaths
    1.14
    verwijspagina
    1.13
     EconPapers
    1.10
     الرياضيه
    1.07
    Act Density 0.111%

    No Known Activations