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

    Neuronpedia

    INDEX
    Explanations

    UK country codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doua
    0.41
    țiilor
    0.39
    했고
    0.39
     거고
    0.39
    었고
    0.39
    وره
    0.38
    이고
    0.37
    ികളും
    0.36
     soie
    0.36
     mezcla
    0.36
    POSITIVE LOGITS
     لهذه
    0.44
     لهذا
    0.43
     ஆகியவற்ற
    0.41
     সবগুলো
    0.40
     ដើម្បី
    0.40
    案例
    0.39
     these
    0.39
    いずれ
    0.39
    这些
    0.38
     colocando
    0.38
    Act Density 0.076%

    No Known Activations