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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and court proceedings

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

    code and technical descriptions

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

    This neuron detects preformatted or code-like blocks (HTML <pre> sections and similar document/metadata headings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.68
    Cyfarwyddwr
    -0.67
    الحياه
    -0.64
    MessageOf
    -0.63
     للاسماء
    -0.62
     <=",
    -0.59
     pinulongan
    -0.57
     تضيفلها
    -0.57
     >=",
    -0.56
    styleType
    -0.53
    POSITIVE LOGITS
     []:
    0.57
    ագրություններ
    0.51
    /**
    0.48
     intptr
    0.47
    Clik
    0.46
    tvguidetime
    0.45
    內容簡介
    0.45
    UserScript
    0.44
     समीक्षक
    0.43
    0.43
    Act Density 0.016%

    No Known Activations