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

    Neuronpedia

    INDEX
    Explanations

    code assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bered
    0.44
     Показа
    0.43
    trimmed
    0.39
    _{\{
    0.38
     correctly
    0.38
    igned
    0.37
    実施
    0.37
     Annotated
    0.37
     explained
    0.37
    改正
    0.37
    POSITIVE LOGITS
    Assert
    1.07
     assert
    1.04
     Assert
    1.04
     assertions
    1.00
     asserting
    0.96
    assert
    0.94
    Assertions
    0.93
     asserts
    0.91
     assertion
    0.90
     assertive
    0.81
    Act Density 0.007%

    No Known Activations