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

    Neuronpedia

    INDEX
    Explanations

    residing at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     samym
    0.68
     सुनिश्चित
    0.67
    kannya
    0.65
    గ్ర
    0.64
    evším
    0.63
    ûn
    0.62
    Dentro
    0.62
    cientes
    0.61
     системе
    0.61
    ଲା
    0.61
    POSITIVE LOGITS
     of
    2.67
    of
    2.05
     của
    1.96
     ofthe
    1.90
    ของ
    1.74
    Of
    1.63
     של
    1.60
     của
    1.58
     Of
    1.56
    ຂອງ
    1.55
    Act Density 0.005%

    No Known Activations