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

    Neuronpedia

    INDEX
    Explanations

    specific programming variables and function parameters in code

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

    Code, usernames, or identifiers

    np_acts-logits-general · gemini-2.0-flash

    renderer, variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.73
    -
    -0.71
     
    -0.68
    '
    -0.62
    ;
    -0.61
    !
    -0.61
    .
    -0.61
    ↵
    -0.60
    ],
    -0.57
    ","
    -0.56
    POSITIVE LOGITS
    RenderAtEndOf
    1.56
    tvguidetime
    1.48
     للمعارف
    1.46
    ValueStyle
    1.44
     مشين
    1.40
    expandindo
    1.40
     كومونز
    1.38
     propOrder
    1.38
    GEBURTSDATUM
    1.38
     disambiguazione
    1.38
    Act Density 0.277%

    No Known Activations