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

    Neuronpedia

    INDEX
    Explanations

    simply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deberían
    0.46
    Almost
    0.45
     presque
    0.44
     debería
    0.44
    แน่นอน
    0.43
     prawie
    0.43
     dovrebbe
    0.42
     लगभग
    0.42
     almost
    0.41
     Almost
    0.41
    POSITIVE LOGITS
     simply
    1.73
     просто
    1.60
     semplicemente
    1.58
    simply
    1.50
     simplesmente
    1.48
     simplemente
    1.45
    Simply
    1.40
     jednostavno
    1.39
     Simply
    1.38
     simplement
    1.38
    Act Density 0.017%

    No Known Activations