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

    Neuronpedia

    INDEX
    Explanations

    una vez

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いくつか
    0.66
     guzt
    0.63
     возможно
    0.61
    மைச்சர்
    0.61
    ielleicht
    0.60
    이라
    0.59
     başlayalım
    0.59
    यानक
    0.58
     ድረስ
    0.58
    뒹
    0.58
    POSITIVE LOGITS
     when
    6.24
    when
    5.83
     quando
    5.61
     cuando
    5.47
    When
    5.23
     When
    5.23
     khi
    4.93
     WHEN
    4.92
     когда
    4.87
     ketika
    4.70
    Act Density 1.877%

    No Known Activations