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

    Neuronpedia

    INDEX
    Explanations

    star patterns and logic tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     +=
    0.42
     aton
    0.41
    >**
    0.39
    ァ
    0.38
    زن
    0.37
     FER
    0.37
    +=
    0.36
    FEC
    0.36
    డంలో
    0.36
    anamh
    0.35
    POSITIVE LOGITS
    llllllll
    0.58
    llllll
    0.56
    cccccc
    0.46
    五个
    0.45
    cccc
    0.43
    四个
    0.43
     Economies
    0.43
     পাঁচটি
    0.41
    Hobbies
    0.41
    lllll
    0.40
    Act Density 0.001%

    No Known Activations