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

    Neuronpedia

    INDEX
    Explanations

    legal proceedings

    np_max-act · gemini-2.0-flash

    Neuron 4 looks for legal procedural language—terms and verbs related to filing or moving motions, petitions, or appeals under procedural rules.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    subtract
    -0.07
    ğ
    -0.06
     Selector
    -0.06
     bathrooms
    -0.06
    ド
    -0.06
     Abdel
    -0.06
    ']).
    -0.06
    ovanou
    -0.06
     Store
    -0.06
     circulated
    -0.06
    POSITIVE LOGITS
    (In
    0.06
    [unit
    0.06
     tốt
    0.06
     naughty
    0.06
    crease
    0.06
    [String
    0.06
     kW
    0.06
    pagina
    0.06
     wah
    0.06
     سنة
    0.06
    Act Density 0.018%

    No Known Activations