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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pyplot
    0.69
     ஐந்து
    0.68
     sche
    0.68
     ट्रिपल
    0.67
     five
    0.66
    五个
    0.66
     पाँच
    0.65
     factual
    0.64
     пяти
    0.64
     fifth
    0.63
    POSITIVE LOGITS
     eighteen
    1.09
     Sixteen
    0.82
     २४
    0.81
     sixteen
    0.81
    Twenty
    0.78
     Twenty
    0.78
     двадцать
    0.72
     ১৮
    0.72
    十八
    0.71
    ২৪
    0.70
    Act Density 0.075%

    No Known Activations