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

    Neuronpedia

    INDEX
    Explanations

    structured document elements and references within text

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

    documentation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.49
    SequentialGroup
    -0.45
    ❉
    -0.42
     Decke
    -0.42
    ConverterFactory
    -0.40
    LabelTagHelper
    -0.39
    ↹
    -0.39
    oredCriteria
    -0.38
    Corne
    -0.37
    QtCore
    -0.36
    POSITIVE LOGITS
     ostavi
    0.45
    ChildScrollView
    0.44
     ویکی‌پدی
    0.43
     femininos
    0.42
     religione
    0.42
    ModelAdmin
    0.41
     걸
    0.41
     Götter
    0.40
     ancaman
    0.40
     învă
    0.40
    Act Density 1.215%

    No Known Activations