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

    Neuronpedia

    INDEX
    Explanations

    instances of headers in multipart or structured content

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

    technical header usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.46
    })();
    -0.37
    PageModule
    -0.37
     Mazz
    -0.35
    ile
    -0.34
     Raffa
    -0.33
     infamous
    -0.33
    一旁的
    -0.33
     Tib
    -0.32
     اغ
    -0.32
    POSITIVE LOGITS
    Header
    2.88
     Header
    2.41
    HEADER
    1.77
     Headers
    1.66
     HEADER
    1.64
     header
    1.63
    getHeader
    1.53
    Headers
    1.36
     headers
    1.32
    PHeader
    1.29
    Act Density 0.003%

    No Known Activations