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

    Neuronpedia

    INDEX
    Explanations

    Then I should see Assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hensive
    0.40
     نیاز
    0.39
     উপল
    0.38
     walled
    0.38
    郯
    0.38
    0.38
     nevoie
    0.37
     захворю
    0.37
     нужда
    0.37
    ALA
    0.37
    POSITIVE LOGITS
     expected
    1.79
    expected
    1.66
     Expected
    1.63
    Expected
    1.59
     EXPECT
    1.41
    EXPECT
    1.39
     expect
    1.37
    expect
    1.30
     assert
    1.29
    assert
    1.27
    Act Density 0.041%

    No Known Activations