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

    Neuronpedia

    INDEX
    Explanations

    test definitions inside code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mozzarella
    0.44
    TrackAngle
    0.43
     rosin
    0.41
    ➸
    0.41
     rameaux
    0.40
    🦐
    0.40
    اونلو
    0.40
     automático
    0.40
     hyaluronic
    0.40
    ้ว
    0.39
    POSITIVE LOGITS
     test
    1.02
    test
    0.96
     tests
    0.95
    Test
    0.84
     Test
    0.83
    tests
    0.82
     Tests
    0.80
    测试
    0.77
    Tests
    0.75
     테스트
    0.75
    Act Density 0.013%

    No Known Activations