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

    Neuronpedia

    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लिए
    0.87
    сього
    0.85
    !\!\
    0.77
    wijl
    0.77
    "\
    0.76
     shillings
    0.76
    що
    0.75
     Laat
    0.75
     seme
    0.74
     işle
    0.74
    POSITIVE LOGITS
    地方
    1.18
    新技术
    0.99
     xlab
    0.90
     entityManager
    0.88
    да
    0.87
    大脑
    0.87
    数据
    0.87
    নাকে
    0.86
    metros
    0.86
     wiggle
    0.84
    Act Density 0.094%

    No Known Activations