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

    Neuronpedia

    INDEX
    Explanations

    breakdown or build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ジ
    0.48
    ථ
    0.48
     ঋণ
    0.46
    これは
    0.46
     これ
    0.45
     significantly
    0.45
     重要
    0.44
    IFT
    0.44
    テ
    0.44
    できる
    0.44
    POSITIVE LOGITS
    Пра
    0.51
     проблемы
    0.49
     бе
    0.47
    咶
    0.46
     Spacious
    0.46
     Hiking
    0.46
     бу
    0.45
    騫
    0.45
     Attribute
    0.44
    嘈
    0.44
    Act Density 0.000%

    No Known Activations