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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their usage in legal or technical contexts

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

    Abbreviations or acronyms in parentheses

    np_acts-logits-general · gemini-2.0-flash

    acronyms in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.61
     Eſ
    -0.59
     Majefty
    -0.58
     itſelf
    -0.56
     Monfieur
    -0.56
     ſeveral
    -0.56
     beſt
    -0.55
     himſelf
    -0.55
     Houſe
    -0.55
     poffible
    -0.53
    POSITIVE LOGITS
    MigrationBuilder
    1.02
    Personensuche
    0.86
     Roskov
    0.78
     defaultstate
    0.77
    <bos>
    0.67
    IsMutable
    0.66
    ArrowToggle
    0.65
    verwijspagina
    0.65
    Искәрмәләр
    0.64
     Meksiku
    0.64
    Act Density 0.576%

    No Known Activations