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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs and syntax, particularly in the context of data structures and functions

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

    Code, math, or special characters ending lines

    np_acts-logits-general · gemini-2.0-flash

    code and math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.63
     للمعارف
    -0.61
     Administrativna
    -0.50
     Superhost
    -0.48
    Спољашње
    -0.47
    Mvc
    -0.46
    Vidite
    -0.46
    nesc
    -0.44
    UPAC
    -0.44
    حياتها
    -0.43
    POSITIVE LOGITS
    </tbody>
    0.72
    Personensuche
    0.65
    ){}
    0.62
    ↵
    0.59
     {}));
    0.58
    AndEndTag
    0.56
    setDo
    0.55
    ViewFeatures
    0.54
    :''
    0.52
    şiv
    0.51
    Act Density 0.432%

    No Known Activations