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

    Neuronpedia

    INDEX
    Explanations

    references to various types of tests and their results

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

    test and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.60
    GOTREF
    -0.57
    writeFieldEnd
    -0.54
     المعيارى
    -0.52
    PropertyChanging
    -0.52
    GraphicsUnit
    -0.51
    copg
    -0.50
    AddTagHelper
    -0.50
     aapt
    -0.49
     oprot
    -0.49
    POSITIVE LOGITS
     test
    1.25
     tests
    1.18
     testing
    1.09
     Test
    1.08
     Tests
    1.05
     tester
    0.98
     TEST
    0.93
     Testing
    0.92
     TESTS
    0.90
    Test
    0.88
    Act Density 0.111%

    No Known Activations