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

    Neuronpedia

    INDEX
    Explanations

    controlling print end parameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    w
    0.42
    𝔼
    0.42
    g
    0.41
    द्व
    0.41
     swapped
    0.40
    thew
    0.40
    fear
    0.40
    touch
    0.40
    k
    0.40
    ích
    0.39
    POSITIVE LOGITS
     ನಾವು
    0.42
     viktigt
    0.42
     ৫
    0.42
     بالإضافة
    0.41
     আমরা
    0.41
     solar
    0.40
     중요하다
    0.40
     townhouse
    0.40
     ഇവിടെ
    0.40
     ပဲ
    0.40
    Act Density 0.001%

    No Known Activations