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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure

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

    Punctuation and symbols in code/data

    np_acts-logits-general · gemini-2.0-flash

    code context, often followed by `...`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ）』
    -0.69
    Portail
    -0.69
    '},
    -0.59
     دریافت‌شده
    -0.59
    tagHelperRunner
    -0.58
    !")
    -0.58
    tinyos
    -0.55
     Roskov
    -0.55
    تقاوى
    -0.52
     ErrIntOverflow
    -0.52
    POSITIVE LOGITS
     ...
    2.12
    ...
    2.04
    …
    1.87
     …
    1.82
    ....
    1.69
    ...,
    1.67
    ...)
    1.65
    ……
    1.60
    ….
    1.58
    ...</
    1.57
    Act Density 0.383%

    No Known Activations