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

    Neuronpedia

    INDEX
    Explanations

    box its own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    സ്ട
    0.64
    getOutputStream
    0.62
    ্রেক
    0.61
    笅
    0.60
    าร
    0.60
    inken
    0.60
     poblaciones
    0.60
    orrag
    0.59
    න්ද
    0.58
     glared
    0.58
    POSITIVE LOGITS
     own
    4.93
    自己的
    4.34
     Own
    4.21
     propia
    4.13
     eigenen
    4.07
     eigene
    4.05
     própria
    4.02
     propio
    3.99
    Own
    3.93
     włas
    3.91
    Act Density 1.562%

    No Known Activations