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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    details pertaining to legal cases and court proceedings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects document section headings and numbered or labeled structural markers (e.g. "FACTUAL AND PROCEDURAL HISTORY", roman numerals, section titles).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sta
    -0.07
    ّ
    -0.06
     آماده
    -0.06
    �
    -0.06
     lul
    -0.06
    912
    -0.06
     Assad
    -0.06
     Zach
    -0.06
    删除成功
    -0.05
    ................
    -0.05
    POSITIVE LOGITS
    \Module
    0.07
    πα
    0.07
    战
    0.07
     웃
    0.07
    牌
    0.07
    -last
    0.07
     Attribute
    0.06
     Oper
    0.06
    戰
    0.06
    امي
    0.06
    Act Density 0.020%

    No Known Activations