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

    Neuronpedia

    INDEX
    Explanations

    significant references to entities or objects within a text

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

    United States, fatty acids, blood cholesterol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.52
    LabelTagHelper
    -0.45
    InjectAttribute
    -0.44
    <bos>
    -0.42
    OwnProperty
    -0.38
    RTEX
    -0.36
    biscuit
    -0.35
     CreateTagHelper
    -0.33
    Демографія
    -0.32
    saraba
    -0.32
    POSITIVE LOGITS
    expandindo
    0.65
    0.57
     ویکی‌پدی
    0.54
    __':
    0.50
     recommandons
    0.50
    \{\\
    0.48
     Administrativna
    0.48
    ########.
    0.48
    ACHUSET
    0.47
    verifyException
    0.47
    Act Density 0.005%

    No Known Activations