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

    Neuronpedia

    INDEX
    Explanations

    predict the most probable sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ندر
    0.43
    ភ្ជាប់
    0.42
    ви
    0.42
    修为
    0.41
    方向に
    0.40
    构
    0.40
     পরিমাণ
    0.40
     dropper
    0.40
    ุณ
    0.39
    机制
    0.39
    POSITIVE LOGITS
     Semua
    0.48
    ﻩ
    0.45
    Entonces
    0.44
    AlertDialog
    0.43
    BJP
    0.42
    Leftrightarrow
    0.42
     Оста
    0.42
    translation
    0.41
    Translation
    0.41
    "
    0.41
    Act Density 0.002%

    No Known Activations