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

    Neuronpedia

    INDEX
    Explanations

    booking appointments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.49
     карто
    0.47
     пер
    0.46
    ethod
    0.45
    acre
    0.44
     be
    0.43
    mercial
    0.43
    s
    0.43
    les
    0.43
     먹
    0.43
    POSITIVE LOGITS
    िओ
    0.59
    روج
    0.57
    ந்திர
    0.51
    کان
    0.50
    یکا
    0.49
    廻
    0.46
    栞
    0.45
    shifts
    0.45
    ляция
    0.45
    ان
    0.45
    Act Density 0.000%

    No Known Activations