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

    Neuronpedia

    INDEX
    Explanations

    credit rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Carp
    0.54
     গঙ্গ
    0.47
    加热
    0.46
    通风
    0.45
     bào
    0.43
    浈
    0.43
    机器
    0.43
    羟
    0.43
     whiteboard
    0.43
    蛔
    0.43
    POSITIVE LOGITS
     ratings
    1.59
     rating
    1.56
    ratings
    1.39
    rating
    1.38
     Ratings
    1.36
    Rating
    1.35
     Rating
    1.35
     рейтин
    1.32
     रेटिंग
    1.30
    Ratings
    1.26
    Act Density 0.010%

    No Known Activations