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

    Neuronpedia

    INDEX
    Explanations

    for a purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ቦታ
    0.39
     باتوں
    0.39
    latego
    0.38
     によって
    0.38
     እንቅ
    0.38
    を買
    0.38
    を踏
    0.37
    راہیم
    0.36
     kuhusu
    0.36
    怛
    0.36
    POSITIVE LOGITS
    สำหรับการ
    1.18
     для
    1.04
    для
    0.97
     für
    0.91
     để
    0.90
     for
    0.89
    for
    0.88
    សម្រាប់ការ
    0.88
     pentru
    0.86
     untuk
    0.86
    Act Density 0.018%

    No Known Activations