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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron activates on capitalized name and organization tokens (proper nouns, initials, and acronyms) in legal headings and party listings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .fp
    -0.07
    _skb
    -0.06
    ำ
    -0.06
    orderby
    -0.06
    Based
    -0.06
     سبز
    -0.06
    fullname
    -0.06
     dựng
    -0.06
    όδ
    -0.06
     lắp
    -0.06
    POSITIVE LOGITS
     retailer
    0.07
     courses
    0.07
     cuts
    0.06
     celebrates
    0.06
     Define
    0.06
     recall
    0.06
     difficulty
    0.06
    efe
    0.06
     Boolean
    0.06
    (xx
    0.06
    Act Density 0.016%

    No Known Activations