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

    Neuronpedia

    INDEX
    Explanations

    individually printing or appending elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ian
    0.50
     ersten
    0.43
    ia
    0.42
     మొదటి
    0.39
    ieten
    0.38
     års
    0.37
     zatem
    0.37
     erstes
    0.37
    aze
    0.37
     első
    0.37
    POSITIVE LOGITS
     individually
    0.50
    個別
    0.47
     ஒவ்வ
    0.43
    subTest
    0.41
    separate
    0.41
     separate
    0.40
     separately
    0.40
    个体
    0.39
    鱼
    0.39
    每个
    0.39
    Act Density 0.586%

    No Known Activations