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

    Neuronpedia

    INDEX
    Explanations

    formatting or metadata indicators within code or documentation

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

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.56
     HttpStatusCode
    -0.47
    存于互联网档案馆
    -0.46
    цездатний
    -0.44
    MigrationBuilder
    -0.43
     disambiguazione
    -0.42
    mergeFrom
    -0.40
    RTSC
    -0.39
     &___
    -0.38
    Халык
    -0.38
    POSITIVE LOGITS
    statt
    0.48
    katy
    0.47
    DebuggerNonUser
    0.46
    madi
    0.46
     tokopedia
    0.45
     Winaray
    0.45
    isier
    0.45
    véni
    0.45
    pannt
    0.45
    hoots
    0.45
    Act Density 0.027%

    No Known Activations