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

    Neuronpedia

    INDEX
    Explanations

    references to classes and functions within a programming context, particularly those related to UI components and import statements

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

    Code, symbols, or uncommon punctuation

    np_acts-logits-general · gemini-2.0-flash

    scientific notation and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.94
    ↵↵
    -0.75
    </tbody>
    -0.71
    ?}",
    -0.59
     işaret
    -0.57
    ();}
    -0.55
    );}
    -0.55
    "></
    -0.54
    ></
    -0.54
     and
    -0.53
    POSITIVE LOGITS
     disambiguazione
    1.24
     متعلقه
    1.17
    rungsseite
    1.15
     propOrder
    1.12
     للمعارف
    1.06
    PreferredItem
    1.04
     للاسماء
    0.99
    Cyfeiriadau
    0.99
    oredCriteria
    0.98
    ThroughAttribute
    0.97
    Act Density 0.318%

    No Known Activations