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

    Neuronpedia

    INDEX
    Explanations

    syntactical structures and formatting elements often found in technical or legal documents

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

    Code, math, or specialized notation

    np_acts-logits-general · gemini-2.0-flash

    symbols and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.64
    abestanden
    -0.63
    AndEndTag
    -0.61
    expandindo
    -0.57
     iconst
    -0.57
    ichthys
    -0.56
    مصادر
    -0.54
    erol
    -0.54
    Tembelea
    -0.53
    Hochspringen
    -0.52
    POSITIVE LOGITS
    AllAfrica
    0.59
    كويكب
    0.57
    FieldBuilder
    0.51
    steamcommunity
    0.47
    ····
    0.47
     समीक्षक
    0.47
    Personensuche
    0.47
    ][]
    0.46
    ArgsConstructor
    0.46
     entanto
    0.45
    Act Density 0.032%

    No Known Activations