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

    Neuronpedia

    INDEX
    Explanations

    within [timeframe]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হাসানের
    0.44
     любой
    0.43
     любые
    0.43
     любых
    0.42
     quaisquer
    0.42
     обслуживание
    0.41
    任何
    0.41
     कोणताही
    0.41
    怀疑
    0.40
     bebé
    0.39
    POSITIVE LOGITS
     эта
    0.46
     श
    0.41
     вас
    0.41
    できた
    0.40
     தந்த
    0.39
    ,
    0.39
     hort
    0.39
     Executor
    0.39
     예
    0.38
    给了
    0.37
    Act Density 0.001%

    No Known Activations