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

    Neuronpedia

    INDEX
    Explanations

    C/C++ include statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تاجها
    0.43
     rang
    0.40
    こだ
    0.39
     дизайнер
    0.39
     ConsoleKey
    0.39
     поступа
    0.38
     collage
    0.38
     গোষ্ঠী
    0.37
     astrophysics
    0.37
    쏨
    0.37
    POSITIVE LOGITS
    我們
    0.43
    ibouti
    0.42
    .!
    0.42
     પગ
    0.41
    lips
    0.39
    ުމ
    0.38
     ডে
    0.38
     această
    0.38
     oftentimes
    0.38
    urney
    0.38
    Act Density 0.000%

    No Known Activations