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

    Neuronpedia

    INDEX
    Explanations

    testing imports and setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tests
    0.63
     Tests
    0.53
     TESTS
    0.48
     тестирование
    0.47
     टेस्ट
    0.46
     testing
    0.44
     테스트
    0.43
     Testing
    0.43
    测试
    0.42
     тест
    0.42
    POSITIVE LOGITS
    getFullYear
    0.39
    ovna
    0.39
    流程
    0.38
     कार्बो
    0.38
     결과
    0.37
     horseshoe
    0.37
    herjee
    0.37
     फार्मूला
    0.37
    面包
    0.37
    ovana
    0.37
    Act Density 0.001%

    No Known Activations