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

    Neuronpedia

    INDEX
    Explanations

    generic mathematical symbols and expressions

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

    mathematical expressions with functions and variables

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that are part of mathematical/LaTeX-style expressions (equations, operators, formulas and math-mode constructs).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ########.
    -0.91
     esternos
    -0.67
    +#+
    -0.66
    Autoritní
    -0.65
     disambiguazione
    -0.64
     EconPapers
    -0.61
    -0.60
    <unused52>
    -0.59
    <unused41>
    -0.59
    <unused17>
    -0.59
    POSITIVE LOGITS
     arşivlendi
    0.43
     Grüße
    0.36
     Grüsse
    0.35
     aluguel
    0.31
     verwijderen
    0.30
     wzglę
    0.30
    strado
    0.29
    PerformLayout
    0.29
     voeren
    0.29
     installieren
    0.29
    Act Density 8.645%

    No Known Activations