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

    Neuronpedia

    INDEX
    Explanations

    Correct answers and portfolios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTEST
    1.27
    所以在
    1.19
    OCUS
    1.16
     ſ
    1.14
    ⺊
    1.12
    昍
    1.12
    菒
    1.10
    ÉRI
    1.10
    レンチ
    1.10
    㬰
    1.09
    POSITIVE LOGITS
     could
    1.20
    kę
    1.14
     (
    1.11
     resembles
    1.10
     varies
    1.10
    s
    1.10
     combines
    1.09
    (
    1.08
    （
    1.07
     constitutes
    1.03
    Act Density 0.000%

    No Known Activations