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

    Neuronpedia

    INDEX
    Explanations

    user reviews and ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.59
    Let
    0.59
    να
    0.58
     It
    0.57
    It
    0.56
     groin
    0.56
    \</
    0.55
     spinal
    0.53
    发展
    0.52
    </strong>
    0.52
    POSITIVE LOGITS
     reviews
    0.86
     отзывы
    0.79
     Reviews
    0.74
    Reviews
    0.71
    reviews
    0.69
    v
    0.67
     hotels
    0.64
     리뷰
    0.64
     Bewertungen
    0.63
    три
    0.63
    Act Density 0.042%

    No Known Activations