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

    Neuronpedia

    INDEX
    Explanations

    considerations and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soll
    0.39
     bedo
    0.35
    閎
    0.35
     afraid
    0.35
    eteer
    0.34
     सावधान
    0.34
     เรีย
    0.34
    щ
    0.34
     soldier
    0.34
     distrust
    0.33
    POSITIVE LOGITS
     অক্ষ
    0.39
    vertine
    0.39
    тити
    0.39
    ogloss
    0.38
     термин
    0.38
    trashItem
    0.37
     টিক্কা
    0.37
    cmml
    0.37
     उपलब्धता
    0.37
     रवा
    0.37
    Act Density 0.006%

    No Known Activations