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

    Neuronpedia

    INDEX
    Explanations

    reducer and dispatch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countered
    0.48
    ringle
    0.41
    ברים
    0.41
    ρέπει
    0.40
     дзяржа
    0.39
     রাষ্ট্র
    0.39
    ombang
    0.39
    Malaysia
    0.39
    ності
    0.38
    getState
    0.38
    POSITIVE LOGITS
     Tut
    0.40
     Friction
    0.40
     Cay
    0.40
     Send
    0.39
     प्रतिकूल
    0.39
     Sar
    0.38
     Employee
    0.37
     উদ্বেগ
    0.37
    鱉
    0.37
     Benito
    0.37
    Act Density 0.002%

    No Known Activations