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

    Neuronpedia

    INDEX
    Explanations

    operation

    np_max-act · gemini-2.0-flash

    The neuron activates on structural keywords of an OpenAPI/Swagger specification (e.g. “openapi,” “paths,” “components,” “servers,” “operationId,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dissect
    -0.07
     Robbins
    -0.07
    .market
    -0.06
    .Record
    -0.06
    BUFF
    -0.06
    ENCES
    -0.06
     mars
    -0.06
    _notice
    -0.06
    ,//
    -0.06
     DataAccess
    -0.06
    POSITIVE LOGITS
    [L
    0.07
     MC
    0.07
    .Initial
    0.06
    Freedom
    0.06
    ープ
    0.06
     Elle
    0.06
    indhoven
    0.06
     تفاوت
    0.06
    -abortion
    0.06
     орг
    0.06
    Act Density 0.011%

    No Known Activations