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

    Neuronpedia

    INDEX
    Explanations

    unit tests and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.65
    to
    0.58
    นี้
    0.56
     Pleistocene
    0.55
     Louvre
    0.54
    al
    0.54
     To
    0.54
    that
    0.54
    st
    0.54
     that
    0.53
    POSITIVE LOGITS
    ี
    0.51
     bá
    0.51
    tdd
    0.50
    μές
    0.49
     up
    0.48
     UnitTest
    0.48
    ستون
    0.48
    ブ
    0.48
    透露
    0.48
     distintas
    0.47
    Act Density 0.008%

    No Known Activations