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

    Neuronpedia

    INDEX
    Explanations

    enjoy your meal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಡೇ
    0.40
     desperate
    0.39
     degeneracy
    0.39
     vogliamo
    0.38
     carbs
    0.38
    我們先
    0.38
    стные
    0.37
    我们要
    0.37
    なども
    0.36
    شنامه
    0.36
    POSITIVE LOGITS
     voila
    1.15
     voilà
    1.05
     Voilà
    1.04
     Enjoy
    0.79
     이제
    0.79
    即可
    0.79
    Voilà
    0.79
     now
    0.75
    Enjoy
    0.74
     enjoy
    0.72
    Act Density 0.058%

    No Known Activations