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

    Neuronpedia

    INDEX
    Explanations

    equations with x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቿ
    0.39
    謁
    0.38
     ajutor
    0.37
     hives
    0.36
    ində
    0.36
    uela
    0.35
     trợ
    0.35
     gatherings
    0.35
    toe
    0.35
     wreaths
    0.34
    POSITIVE LOGITS
     x
    0.70
     एक्सयर
    0.57
     Linear
    0.50
    Linear
    0.49
     линей
    0.49
    x
    0.49
    푥
    0.49
    𝒙
    0.47
    linear
    0.44
     х
    0.44
    Act Density 0.016%

    No Known Activations