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

    Neuronpedia

    INDEX
    Explanations

    code testing

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens related to unit‐test code—e.g. “test,” “mock,” “verify,” “Mockito,” etc.—i.e. testing and mocking API calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    function calls related to mocking in testing frameworks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     test
    -0.07
     Brands
    -0.07
    flies
    -0.07
     Tor
    -0.06
    Light
    -0.06
    Shot
    -0.06
     geçmiş
    -0.06
    εφ
    -0.06
     recruiters
    -0.06
     restore
    -0.06
    POSITIVE LOGITS
     prejud
    0.07
     TouchableOpacity
    0.06
     علاق
    0.06
     drafted
    0.06
    (hWnd
    0.06
    295
    0.06
    -most
    0.06
    (pair
    0.06
     件
    0.06
    (guid
    0.06
    Act Density 0.041%

    No Known Activations