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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming, specifically with a focus on Swift and Protobuf syntax

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

    Punctuation and symbols in code or text

    np_acts-logits-general · gemini-2.0-flash

    specific programming or unusual words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.90
     
    -0.82
     and
    -0.80
     in
    -0.77
     (
    -0.77
    .
    -0.75
     for
    -0.73
    The
    -0.71
    -
    -0.70
    In
    -0.68
    POSITIVE LOGITS
     незавершена
    1.75
    Personensuche
    1.68
     Савезне
    1.62
     Roskov
    1.58
    تقاوى
    1.50
    Autoritní
    1.49
     الحره
    1.47
    Geplaatst
    1.43
     CreateTagHelper
    1.43
    uxxxx
    1.42
    Act Density 0.524%

    No Known Activations