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

    Neuronpedia

    INDEX
    Explanations

    testing and requests for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Begriff
    0.64
    itionen
    0.62
    findpost
    0.61
    ෝජ
    0.59
     وزی
    0.59
    ූප
    0.59
    FDMA
    0.58
     hoạch
    0.58
    ossians
    0.57
     zprac
    0.57
    POSITIVE LOGITS
     testing
    5.15
     test
    5.13
    测试
    4.95
     Testing
    4.86
     tests
    4.75
     Test
    4.70
    Testing
    4.62
    Test
    4.55
     테스트
    4.52
    測試
    4.48
    Act Density 1.944%

    No Known Activations