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

    Neuronpedia

    INDEX
    Explanations

    lists and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    があった
    0.36
     }}$.
    0.34
    ``.
    0.32
     الجامعة
    0.32
    .\"
    0.31
     час
    0.30
    "/>.
    0.30
    int
    0.30
    ‌آ
    0.30
    нимание
    0.30
    POSITIVE LOGITS
    -,
    0.74
     તેમજ
    0.63
    、
    0.62
    以及
    0.54
     비롯
    0.52
     oraz
    0.51
     maupun
    0.51
     և
    0.51
    ﹑
    0.51
     وكذلك
    0.50
    Act Density 0.103%

    No Known Activations