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

    Neuronpedia

    INDEX
    Explanations

    comparing items for decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IFT
    0.49
    0
    0.48
    ジ
    0.48
    テ
    0.47
    これは
    0.46
     significantly
    0.46
    ථ
    0.46
     ঋণ
    0.45
    IE
    0.45
    大切な
    0.45
    POSITIVE LOGITS
     бе
    0.48
     Spacious
    0.48
     бу
    0.48
     проблемы
    0.48
    Пра
    0.47
     кора
    0.47
     Мер
    0.47
     ആശ
    0.47
     Animated
    0.45
     makeSound
    0.45
    Act Density 0.001%

    No Known Activations