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

    Neuronpedia

    INDEX
    Explanations

    rating scales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flink
    0.36
    ipients
    0.36
    anlı
    0.35
    どのような
    0.35
     বিব
    0.35
     tunnel
    0.34
    specified
    0.34
    splitext
    0.34
    //}
    0.33
    organizations
    0.33
    POSITIVE LOGITS
     rating
    1.09
     Rating
    1.00
    Rating
    0.92
     ratings
    0.91
    rating
    0.90
     रेटिंग
    0.88
     рейтинг
    0.87
     score
    0.85
     Ratings
    0.82
     рейтин
    0.82
    Act Density 0.235%

    No Known Activations