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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operations

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

    Fractions and division

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.81
    httphttps
    -0.73
    Tembelea
    -0.66
    InjectAttribute
    -0.65
    tanleria
    -0.62
    AddTagHelper
    -0.60
    BeginContext
    -0.60
    InteropServices
    -0.59
     transfieras
    -0.57
    MessageOf
    -0.56
    POSITIVE LOGITS
     aDecoder
    0.53
     становника
    0.50
     LUMP
    0.48
     canter
    0.48
     asegu
    0.47
     aquarelle
    0.47
     myſelf
    0.47
     Wayback
    0.45
     HIF
    0.45
     păr
    0.45
    Act Density 0.942%

    No Known Activations