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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions and expressions

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

    Followed by "squared", exponents, or variable names

    np_acts-logits-general · gemini-2.0-flash

    squared terms, powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esez
    -0.73
    ScopeManager
    -0.65
    TagMode
    -0.64
    MENAFN
    -0.61
    IVEREF
    -0.60
    Personendaten
    -0.58
     دیکھیے
    -0.57
     nahilalakip
    -0.56
     lenker
    -0.56
    ftagPool
    -0.56
    POSITIVE LOGITS
     squared
    1.50
     square
    1.45
     squares
    1.35
     Square
    1.35
    Square
    1.33
    square
    1.29
    squared
    1.27
     SQUARE
    1.27
    SQUARE
    1.21
    Squared
    1.20
    Act Density 1.178%

    No Known Activations