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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    Mathematical or chemical formulas with brackets

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liffe
    -0.51
     kyse
    -0.45
     Bek
    -0.45
    </h2>
    -0.43
    ándome
    -0.43
    يميديا
    -0.42
    IMPORTED
    -0.42
    Biographical
    -0.41
     Castig
    -0.41
     Hundred
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    1.00
     "..\..\..\
    0.80
    ніципалі
    0.76
    Geplaatst
    0.75
     EClass
    0.70
    modelBuilder
    0.67
     betweenstory
    0.67
    RenderAtEndOf
    0.66
    енча
    0.65
    protoc
    0.64
    Act Density 0.784%

    No Known Activations