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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    information related to programming errors or issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron selectively fires on sentences that describe whether code “works” or “doesn’t work,” i.e. evaluative statements about the functionality or outcome of a code snippet.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Clusters
    -0.07
     Weeks
    -0.07
     Ticket
    -0.07
    .registration
    -0.07
     carefully
    -0.06
    .cd
    -0.06
    921
    -0.06
     Instance
    -0.06
     inspections
    -0.06
     Credits
    -0.06
    POSITIVE LOGITS
    절
    0.06
     suma
    0.06
    تب
    0.06
     XCTAssert
    0.05
    ісля
    0.05
    입
    0.05
     đế
    0.05
     HTMLElement
    0.05
     /****************************************************************
    0.05
     taş
    0.05
    Act Density 0.291%

    No Known Activations