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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or elaborations

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

    my apologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.56
     ویکی‌پدیای
    -0.48
    expandindo
    -0.45
    EndContext
    -0.44
    enterOuterAlt
    -0.44
    queryInterface
    -0.43
    InputTagHelper
    -0.42
     }{@
    -0.42
     CreateTagHelper
    -0.41
    ArrowToggle
    -0.41
    POSITIVE LOGITS
    ंदीखरीदारी
    0.55
     endregion
    0.49
     pinulongan
    0.46
     AssemblyCulture
    0.44
    aarrggbb
    0.42
    挙
    0.40
    挙げ
    0.40
     bat
    0.40
     ever
    0.40
    KURZBESCHREIBUNG
    0.39
    Act Density 0.096%

    No Known Activations