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

    Neuronpedia

    INDEX
    Explanations

    noise reduction and cancellation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.18
     It
    1.07
    the
    1.05
    um
    1.02
    ۔
    0.96
    to
    0.96
    。
    0.96
    <0x0D>
    0.93
    veel
    0.93
    ।
    0.91
    POSITIVE LOGITS
    த
    1.32
    사
    1.30
    ב
    1.18
    त
    1.10
    ক
    1.10
    ل
    1.08
    ก
    1.08
     can
    1.06
    ל
    1.05
    კ
    1.05
    Act Density 0.009%

    No Known Activations