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

    Neuronpedia

    INDEX
    Explanations

    your, YOUR, your, YOUR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    suffixes
    0.61
    ъек
    0.61
    HttpMethod
    0.61
    шек
    0.61
    श्रे
    0.60
     RequestMethod
    0.60
    methods
    0.60
     메서
    0.60
     методов
    0.59
    dirs
    0.59
    POSITIVE LOGITS
     test
    1.29
    test
    1.28
    TEST
    1.27
     TEST
    1.23
    テスト
    1.20
     Test
    1.18
    MyApp
    1.17
    Test
    1.16
    myapp
    1.15
    我的
    1.15
    Act Density 0.264%

    No Known Activations