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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

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

    Numbers enclosed in parentheses

    np_acts-logits-general · gemini-2.0-flash

    (number) followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.77
     AssemblyProduct
    -0.73
    ItemBackground
    -0.72
    RenderAtEndOf
    -0.67
    EndGlobalSection
    -0.66
     tartalomajánló
    -0.66
     فريبيس
    -0.65
    InstrumentedTest
    -0.65
    ParseTree
    -0.61
    TypedDataSet
    -0.60
    POSITIVE LOGITS
    ysan
    0.49
    ESPEC
    0.48
    tention
    0.47
     $("#
    0.47
    idance
    0.47
    ränkt
    0.46
    σια
    0.46
     diambil
    0.45
     sup
    0.44
    ashion
    0.44
    Act Density 0.171%

    No Known Activations