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

    Neuronpedia

    INDEX
    Explanations

    terms related to data structures or programming constructs

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

    Appears after special characters or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    acronyms and specific technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.78
    <eos>
    -0.75
    ,
    -0.71
    ↵↵
    -0.70
    ;
    -0.69
    :
    -0.67
    !
    -0.64
    ?
    -0.64
    ),
    -0.63
    ↵
    -0.63
    POSITIVE LOGITS
     itſelf
    1.21
    PreferredItem
    1.17
     myſelf
    1.16
     Efq
    1.14
     يتيمه
    1.14
     Jefus
    1.13
     الرياضيه
    1.11
     Мексичка
    1.07
     disambiguazione
    1.06
    AsUp
    1.06
    Act Density 0.725%

    No Known Activations