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

    Neuronpedia

    INDEX
    Explanations

    years old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sgn
    0.52
    above
    0.51
    Above
    0.51
    したり
    0.51
    prep
    0.50
    value
    0.50
    >()
    0.49
    NOTE
    0.49
    foreach
    0.49
     выше
    0.49
    POSITIVE LOGITS
     yaşında
    0.74
    歲
    0.66
    岁的
    0.65
     year
    0.62
    岁
    0.62
     meters
    0.59
     година
    0.58
     सदस्यीय
    0.57
     charms
    0.57
     metres
    0.56
    Act Density 0.115%

    No Known Activations