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

    Neuronpedia

    INDEX
    Explanations

    comparison and contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    megapixel
    0.46
     Orden
    0.38
     eksempel
    0.38
     televis
    0.38
     correctamente
    0.37
     quadrilateral
    0.37
    udson
    0.36
     Television
    0.36
     ?:
    0.36
     فولت
    0.36
    POSITIVE LOGITS
    বাসীর
    0.46
     কারণে
    0.45
    elier
    0.43
    いただく
    0.40
     vì
    0.40
     sò
    0.40
     mùa
    0.40
     perks
    0.39
    喂
    0.39
     hoa
    0.39
    Act Density 0.004%

    No Known Activations