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

    Neuronpedia

    INDEX
    Explanations

    antidumping legal cases

    np_max-act · gemini-2.0-flash

    The neuron detects tokens belonging to formal judicial document headers and citations (e.g. court names, docket numbers, and legal-case references).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ke
    -0.06
    UR
    -0.06
     Purpose
    -0.06
     MCC
    -0.06
     JMenuItem
    -0.06
     Package
    -0.06
     Ke
    -0.06
     landmarks
    -0.06
    Emergency
    -0.06
    _offset
    -0.06
    POSITIVE LOGITS
     mourn
    0.08
     halves
    0.08
     raz
    0.07
    منت
    0.07
     NAMES
    0.06
     midd
    0.06
     liv
    0.06
     nationalists
    0.06
    _Box
    0.06
     cols
    0.06
    Act Density 0.004%

    No Known Activations