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

    Neuronpedia

    INDEX
    Explanations

    event following another event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )。
    0.64
    )，
    0.60
    ע
    0.60
    )、
    0.59
     year
    0.58
     menggunakan
    0.57
     kopi
    0.56
     shabd
    0.56
     tenho
    0.55
    尽量
    0.55
    POSITIVE LOGITS
    ės
    0.60
    dt
    0.55
    ás
    0.55
    ಿಸಿದ್ದ
    0.55
    锷
    0.54
    ્સ
    0.53
    đồng
    0.52
    né
    0.51
    Обра
    0.51
    ators
    0.51
    Act Density 0.001%

    No Known Activations