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

    Neuronpedia

    INDEX
    Explanations

    version 3.9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    azaar
    0.70
     takeaway
    0.67
     সমিতি
    0.66
     चुन
    0.66
     wink
    0.65
     wrap
    0.65
     مورد
    0.64
     hour
    0.64
     negotiate
    0.64
     scribble
    0.63
    POSITIVE LOGITS
     Национа
    0.76
     национа
    0.76
     націона
    0.76
     मुकेश
    0.75
     Français
    0.72
    國
    0.72
    比亚
    0.71
     ውስ
    0.70
     ಸಾಮಾನ್ಯ
    0.69
     Bry
    0.68
    Act Density 0.001%

    No Known Activations