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

    Neuronpedia

    INDEX
    Explanations

    someone else, this article, trying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aitu
    0.44
     EAS
    0.43
    ympt
    0.42
     ببین
    0.41
    ここに
    0.39
    但这
    0.39
    ज्ञानिक
    0.39
     این
    0.38
     বলেছিলেন
    0.38
     able
    0.37
    POSITIVE LOGITS
     antifreeze
    0.44
    кер
    0.41
    снаб
    0.41
    gear
    0.40
    畜
    0.40
     يعد
    0.39
     ছিল
    0.39
    Item
    0.39
    lett
    0.39
    reliance
    0.39
    Act Density 0.000%

    No Known Activations