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

    Neuronpedia

    INDEX
    Explanations

    terms associated with options and selections in programming contexts

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

    people, places, and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.47
    modelBuilder
    -0.47
     ujednoznacz
    -0.46
    DeleteBehavior
    -0.46
    SpringBootTest
    -0.45
     typelib
    -0.43
    XmlEnum
    -0.43
     layui
    -0.42
    OrEmpty
    -0.42
    paravant
    -0.40
    POSITIVE LOGITS
    aroa
    0.65
    httphttps
    0.61
    kuuta
    0.50
     Wikimédia
    0.49
    roa
    0.48
     EconPapers
    0.47
    weightedMode
    0.47
     المعيارى
    0.47
    llong
    0.46
    ROIT
    0.44
    Act Density 0.007%

    No Known Activations