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

    Neuronpedia

    INDEX
    Explanations

    you're or you've

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を採用
    0.85
     utilizando
    0.76
    を用いる
    0.75
     pioneered
    0.75
     excellente
    0.73
    boost
    0.67
    だけでなく
    0.66
     utilizzando
    0.66
     sayesinde
    0.66
    elih
    0.66
    POSITIVE LOGITS
    Possible
    1.67
     clues
    1.61
     rumours
    1.52
    дная
    1.47
     احتمال
    1.47
     rumors
    1.45
     alguma
    1.45
     clue
    1.45
     hints
    1.45
    await
    1.43
    Act Density 0.406%

    No Known Activations