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

    Neuronpedia

    INDEX
    Explanations

    every everywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     등으로
    1.01
    それぞれ
    0.94
    などが
    0.92
     anything
    0.91
    Anything
    0.90
     போன்றவற்ற
    0.90
     എന്നിവ
    0.88
     등을
    0.87
     Anything
    0.87
    分别
    0.87
    POSITIVE LOGITS
     every
    5.56
    Every
    5.06
    every
    4.99
     Every
    4.88
     setiap
    3.57
     ogni
    3.46
     EVERY
    3.42
    EVERY
    3.17
     हर
    2.94
     एवरी
    2.86
    Act Density 0.199%

    No Known Activations