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

    Neuronpedia

    INDEX
    Explanations

    references to testing and test-related concepts

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

    test code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.46
    ंदीखरीदारी
    -0.45
     виправивши
    -0.41
     resourceCulture
    -0.38
    ['_
    -0.37
    DebuggerNonUser
    -0.36
    endregion
    -0.35
    oneofs
    -0.35
     Frig
    -0.35
     HFILL
    -0.35
    POSITIVE LOGITS
     test
    0.90
     TEST
    0.87
    test
    0.85
     Test
    0.84
    TEST
    0.83
    Test
    0.78
    テスト
    0.71
     тест
    0.67
    測試
    0.67
    ptest
    0.66
    Act Density 0.064%

    No Known Activations