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

    Neuronpedia

    INDEX
    Explanations

    evidence of testing or validation in a technical context

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

    tests, graphs, data, and experience

    np_acts-logits-general · gemini-2.0-flash

    testing, benchmarks, and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.87
    ########.
    -0.77
    konomi
    -0.62
    المناصب
    -0.62
    HasForeignKey
    -0.61
     MainAxisSize
    -0.60
     rospy
    -0.59
    soever
    -0.58
     Monfieur
    -0.57
    RemoveField
    -0.56
    POSITIVE LOGITS
     test
    2.23
     testing
    2.15
     tests
    2.12
     Test
    1.91
     Testing
    1.90
    Test
    1.82
     Tests
    1.79
    Testing
    1.79
     tested
    1.78
    测试
    1.78
    Act Density 0.820%

    No Known Activations