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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations involving variables and functions

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

    mathematical formulas with square roots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.68
    transQ
    -0.55
    ⟬
    -0.54
     GenerationType
    -0.52
    #
    -0.50
     geométrico
    -0.48
    <unused17>
    -0.47
    <?
    -0.47
    <unused47>
    -0.47
    <unused74>
    -0.47
    POSITIVE LOGITS
     désolés
    0.42
    GTCX
    0.35
    hoeddwyd
    0.34
     Res
    0.34
     separations
    0.33
    GOTREF
    0.32
    setIsLoading
    0.31
    Folgende
    0.31
     variants
    0.31
    omock
    0.30
    Act Density 0.516%

    No Known Activations