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

    Neuronpedia

    INDEX
    Explanations

    coding-related keywords and return statements

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

    code syntax and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hå
    -0.35
    Щ
    -0.34
    .
    -0.30
    </tr>
    -0.30
    trä
    -0.29
    ];
    -0.29
    mtr
    -0.29
    Hel
    -0.28
    tagHelper
    -0.28
     pula
    -0.28
    POSITIVE LOGITS
     للمعارف
    0.86
    httphttps
    0.77
     propOrder
    0.75
     ویکی‌پدی
    0.71
    AndEndTag
    0.67
    0.66
    protoimpl
    0.64
    transQ
    0.63
    XmlType
    0.63
    rungsseite
    0.63
    Act Density 0.034%

    No Known Activations