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

    Neuronpedia

    INDEX
    Explanations

    fragments associated with programming syntax and structure

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

    LaTeX symbols and math

    np_acts-logits-general · gemini-2.5-flash-lite

    programming-language code tokens and structural keywords (i.e., parts of source code).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    PhysRevLett
    -0.26
    J
    -0.25
    不要
    -0.25
     quoi
    -0.25
     때문
    -0.25
    ,
    -0.23
    the
    -0.23
    I
    -0.23
    The
    -0.23
    多
    -0.23
    POSITIVE LOGITS
     Савезне
    1.37
    :✨
    1.29
     Taktlose
    1.13
    Personendaten
    1.11
    IUrlHelper
    1.09
     ویکی‌پدی
    1.07
    SourceChecksum
    1.02
    MessageOf
    1.02
    webElementXpaths
    1.01
     Италијани
    1.01
    Act Density 5.939%

    No Known Activations