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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or clarity regarding a subject matter

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

    clarity, analysis, studied, known, assessed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.48
    ScopeManager
    -0.47
    yarnpkg
    -0.46
    ineno
    -0.43
    Producción
    -0.43
    AndEndTag
    -0.43
    ungere
    -0.42
    WriteBarrier
    -0.42
    ValueGeneration
    -0.42
    hanger
    -0.41
    POSITIVE LOGITS
    contentLoaded
    0.45
    cookieParser
    0.41
     AssemblyCulture
    0.38
    ExtendWith
    0.37
     initComponents
    0.36
    锈钢
    0.36
    wieś
    0.36
    InstrumentedTest
    0.36
     betweenstory
    0.36
     attes
    0.36
    Act Density 0.396%

    No Known Activations