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

    Neuronpedia

    INDEX
    Explanations

    year or years duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    1.77
    梩
    1.56
    ила
    1.52
     intrav
    1.49
     Così
    1.48
     Beitrag
    1.44
    िन्न
    1.38
    жі
    1.38
     Следу
    1.37
     Сле
    1.37
    POSITIVE LOGITS
    age
    1.63
     écoul
    1.59
    A
    1.58
    !\!\
    1.51
    ite
    1.49
    T
    1.46
    理
    1.46
    ত্ব
    1.43
    Я
    1.41
    基づ
    1.39
    Act Density 0.103%

    No Known Activations