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

    Neuronpedia

    INDEX
    Explanations

    tasks, activities for children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">—
    0.41
    上面的
    0.40
     Promise
    0.39
     Coupled
    0.39
     Prospects
    0.38
     implementation
    0.38
    娄
    0.38
     تطبيق
    0.37
     tą
    0.37
     Sund
    0.37
    POSITIVE LOGITS
    ᖇ
    0.44
    вані
    0.43
    滘
    0.41
    濁
    0.40
    vene
    0.39
    ેચ્છ
    0.38
     carpets
    0.38
    canoe
    0.37
     rén
    0.37
    Perfect
    0.36
    Act Density 4.531%

    No Known Activations