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

    Neuronpedia

    INDEX
    Explanations

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devrait
    0.39
     devraient
    0.39
     اتار
    0.38
     sebenarnya
    0.37
    萦
    0.36
    ટ્સ
    0.36
     sakte
    0.35
     aslında
    0.35
     ออก
    0.35
     условии
    0.35
    POSITIVE LOGITS
    a
    0.50
     unsure
    0.46
    guien
    0.45
     কোনও
    0.44
     किसी
    0.44
     가능하다
    0.43
     alguém
    0.43
     someone
    0.42
    某个
    0.42
    venue
    0.42
    Act Density 0.008%

    No Known Activations