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

    Neuronpedia

    INDEX
    Explanations

    testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.48
    боль
    0.42
     adhipp
    0.42
    ional
    0.40
     Dend
    0.39
    écl
    0.39
    ो
    0.38
     mô
    0.38
    na
    0.38
    issant
    0.38
    POSITIVE LOGITS
     test
    1.24
    测试
    1.23
     testing
    1.18
     테스트
    1.18
     测试
    1.17
    Testing
    1.16
     tested
    1.12
    テスト
    1.11
    測試
    1.11
     Testing
    1.10
    Act Density 0.049%

    No Known Activations