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

    Neuronpedia

    INDEX
    Explanations

    test and simulate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    að
    0.37
    pośred
    0.36
     DENUMIRE
    0.35
    名稱
    0.33
     названия
    0.33
    ದಿ
    0.33
     говори
    0.33
    aryng
    0.32
    臃
    0.32
     feminine
    0.32
    POSITIVE LOGITS
     test
    1.20
    测试
    1.17
     testing
    1.16
     테스트
    1.09
    測試
    1.07
     tests
    1.02
     Testing
    1.00
     simulate
    0.98
     测试
    0.97
    Testing
    0.97
    Act Density 0.536%

    No Known Activations