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

    Neuronpedia

    INDEX
    Explanations

    important numerical values and their relationships in descriptive contexts

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

    Follows certain stop words

    np_acts-logits-general · gemini-2.0-flash

    lists starting with /** or /*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AMILY
    -0.54
    nsic
    -0.54
    ropriate
    -0.54
    prehensive
    -0.54
    — 
    -0.53
    cessite
    -0.49
    kolle
    -0.49
    ductory
    -0.48
    ADORES
    -0.48
    ález
    -0.47
    POSITIVE LOGITS
    IndentedString
    0.96
    awtextra
    0.80
    ArrowToggle
    0.77
    LookAnd
    0.69
     EconPapers
    0.68
     BoxFit
    0.67
     дописавши
    0.67
    余談
    0.65
     disambiguazione
    0.65
    Personensuche
    0.63
    Act Density 0.372%

    No Known Activations