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

    Neuronpedia

    INDEX
    Explanations

    Okay, breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     we
    0.45
     presentamos
    0.44
    我們
    0.43
     chúng
    0.43
     tenemos
    0.43
     우리는
    0.43
     Nous
    0.42
     gratis
    0.42
     আমরা
    0.41
     Founding
    0.41
    POSITIVE LOGITS
    冋
    0.43
    databind
    0.43
    ционер
    0.42
    BusinessType
    0.41
     उद्यान
    0.39
    䀖
    0.39
    老人
    0.39
    ristmas
    0.38
    蚣
    0.37
     Hiram
    0.37
    Act Density 0.003%

    No Known Activations