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

    Neuronpedia

    INDEX
    Explanations

    agreement

    np_max-act · gemini-2.0-flash

    This neuron detects key legal-document and organizational terms—namely capitalized nouns like “Agreement,” “Union,” “Court,” “Plant,” “Policy,” or “Project” that name contracts, entities, or sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    test
    -0.07
    .nodeName
    -0.07
    iyel
    -0.07
     Tester
    -0.07
    にある
    -0.07
    strlen
    -0.07
     بنابر
    -0.07
    річ
    -0.06
     Pelosi
    -0.06
     Retry
    -0.06
    POSITIVE LOGITS
     luz
    0.06
     pits
    0.06
     chanting
    0.06
     sandwiches
    0.06
    _BP
    0.06
    短
    0.06
     contextual
    0.05
    %%↵
    0.05
    sizlik
    0.05
    vous
    0.05
    Act Density 0.011%

    No Known Activations