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

    Neuronpedia

    INDEX
    Explanations

    references to scientific analysis tools and methodologies

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

    Word preceding parentheses

    np_acts-logits-general · gemini-2.0-flash

    scientific analysis and experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hozzáférés
    -0.38
    AddHtmlAttribute
    -0.35
     destrucción
    -0.32
     rozwią
    -0.32
     dinosaurio
    -0.31
     hiér
    -0.30
    )))),
    -0.30
    HasForeignKey
    -0.30
     fonctionnement
    -0.30
     žele
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.99
    verwijspagina
    0.92
    LookAnd
    0.82
    ?),
    0.75
    ?)
    0.75
     ?)
    0.74
    ſelf
    0.73
    !)
    0.72
    ),"
    0.72
    !!)
    0.71
    Act Density 4.599%

    No Known Activations