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

    Neuronpedia

    INDEX
    Explanations

    instructions, descriptions, or components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    এই
    0.34
    របស់
    0.33
     चीजों
    0.33
    Ώ
    0.33
    ຂອງ
    0.33
    ትን
    0.33
     যেগুলো
    0.32
    ওই
    0.32
    ಲ್ಲೂ
    0.32
    újo
    0.32
    POSITIVE LOGITS
     itself
    1.18
    本身
    0.97
    本身的
    0.82
    自体
    0.66
     자체가
    0.62
     자체
    0.61
    内容
    0.58
     description
    0.57
     structure
    0.57
    টি
    0.56
    Act Density 0.282%

    No Known Activations