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

    Neuronpedia

    INDEX
    Explanations

    combination of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ండి
    0.38
    .
    0.36
    )
    0.36
     Cylinder
    0.35
     jednym
    0.34
     einem
    0.33
     Computer
    0.32
     Coconut
    0.32
    ายเป็น
    0.32
     Chocolate
    0.31
    POSITIVE LOGITS
     of
    0.87
     ofthe
    0.69
    ของ
    0.67
     của
    0.64
     των
    0.61
     של
    0.61
     của
    0.58
    ของการ
    0.57
    of
    0.52
     ofx
    0.50
    Act Density 0.109%

    No Known Activations