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

    Neuronpedia

    INDEX
    Explanations

    GPU, hardware, and computing resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    到的
    0.64
    বিভ
    0.64
    冂
    0.63
    얄
    0.63
     hoax
    0.62
    地図
    0.62
    囟
    0.62
     বিভিন্ন
    0.61
    ต่างๆ
    0.61
     pessoal
    0.59
    POSITIVE LOGITS
     Moreover
    0.73
     sehingga
    0.71
     Thus
    0.71
     berkualitas
    0.70
     υψη
    0.67
     ซึ่ง
    0.66
    which
    0.65
     ainsi
    0.65
     GHz
    0.65
    Thus
    0.63
    Act Density 0.000%

    No Known Activations