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

    Neuronpedia

    INDEX
    Explanations

    own / self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    സ്ട
    0.66
    ylene
    0.64
    মতি
    0.63
    DockStyle
    0.62
    উদ্
    0.61
    𝚄
    0.61
    笅
    0.61
    роят
    0.60
    ╯
    0.59
    ോടെ
    0.58
    POSITIVE LOGITS
     own
    4.57
     própria
    4.20
     sendiri
    4.14
     propia
    4.13
     próprio
    4.03
    自己的
    4.01
     propio
    3.99
     próprios
    3.97
     itself
    3.96
    自身
    3.94
    Act Density 1.827%

    No Known Activations