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

    Neuronpedia

    INDEX
    Explanations

    numerical ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     risked
    0.45
    報
    0.43
    の部分
    0.43
     coarser
    0.42
    perplexity
    0.40
    ਤੀ
    0.40
     underlie
    0.40
    Olive
    0.39
     untenable
    0.39
     LIMIT
    0.39
    POSITIVE LOGITS
     Rating
    0.62
     rating
    0.61
    评分
    0.60
     ratings
    0.56
    Rating
    0.54
     stars
    0.54
     estrellas
    0.52
    ⭐️
    0.52
     bintang
    0.52
    Ratings
    0.50
    Act Density 0.062%

    No Known Activations