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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and structures related to programming and code syntax

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

    Code snippets with file paths

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ་་
    -1.13
     Efq
    -1.11
     Majefty
    -1.10
     myſelf
    -1.07
     itſelf
    -1.07
     doubtnut
    -1.01
     photolibrary
    -1.00
     ―――――
    -0.98
    ſelves
    -0.96
     Anſ
    -0.95
    POSITIVE LOGITS
    DoubleQuotes
    0.78
    .*")]
    0.65
     colspan
    0.56
    __(/*!
    0.54
    ÉR
    0.54
     nesta
    0.53
    ValueStyle
    0.52
    lege
    0.51
     pris
    0.51
    hoa
    0.49
    Act Density 0.251%

    No Known Activations