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

    Neuronpedia

    INDEX
    Explanations

    information, timings, innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    綗
    0.44
    ುತ್ತೇವೆ
    0.43
    柰
    0.42
    了他
    0.39
     தலைமை
    0.39
    他在
    0.38
    走了
    0.38
    رځ
    0.38
    नाने
    0.38
    網絡
    0.38
    POSITIVE LOGITS
     മാത്ര
    0.45
    ITY
    0.45
     immersion
    0.44
     поверх
    0.44
     adding
    0.43
     제거
    0.42
     satiety
    0.42
     washable
    0.42
     оки
    0.41
     assessments
    0.41
    Act Density 0.006%

    No Known Activations