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

    Neuronpedia

    INDEX
    Explanations

    rating or score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     l
    0.57
     k
    0.53
     c
    0.52
     h
    0.52
     agriculture
    0.49
     o
    0.49
    崦
    0.49
     ऑयल
    0.48
     частина
    0.45
     an
    0.45
    POSITIVE LOGITS
     rating
    0.60
     ratings
    0.58
    評価
    0.55
    rating
    0.52
    对待
    0.50
    评价
    0.48
    评
    0.48
     рейтинг
    0.47
    评分
    0.47
    Rating
    0.47
    Act Density 0.432%

    No Known Activations