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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting commands related to LaTeX document preparation

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

    technical documentation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.62
    +#+
    -0.59
    featureID
    -0.57
     disambiguazione
    -0.57
     resourceCulture
    -0.54
    Tembelea
    -0.53
     autorytatywna
    -0.52
    GEBURTSDATUM
    -0.49
    */].
    -0.49
    Personensuche
    -0.48
    POSITIVE LOGITS
    ↵↵↵
    0.52
     Abstract
    0.45
     abstract
    0.44
     title
    0.43
    ↵↵↵↵↵
    0.41
    ↵↵↵↵
    0.41
     paper
    0.40
    TITLE
    0.40
     document
    0.40
     setTitle
    0.39
    Act Density 0.001%

    No Known Activations