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

    Neuronpedia

    INDEX
    Explanations

    long periods of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सोन
    0.39
     সাপ্তাহিক
    0.38
    Day
    0.38
    离婚
    0.38
    ябрь
    0.38
     कैलाश
    0.37
     slidesToShow
    0.36
     stayed
    0.36
    第二天
    0.35
    ⊇
    0.35
    POSITIVE LOGITS
     centuries
    3.61
     century
    3.50
     Century
    2.94
    century
    2.91
     Centuries
    2.91
    Century
    2.75
     siglos
    2.75
     siècles
    2.61
     millennia
    2.58
     siglo
    2.56
    Act Density 0.070%

    No Known Activations