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

    Neuronpedia

    INDEX
    Explanations

    code testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পোশাক
    0.45
    salon
    0.44
    充電
    0.43
    raltar
    0.42
     Chamb
    0.42
    Mkv
    0.41
     обре
    0.40
    Dinner
    0.39
    dispers
    0.39
    活動
    0.39
    POSITIVE LOGITS
     tests
    1.35
     test
    1.16
     Tests
    1.16
     testing
    1.08
    测试
    1.07
    Tests
    1.05
     JUnit
    1.05
     Test
    1.05
    tests
    1.02
     unittest
    1.02
    Act Density 0.078%

    No Known Activations