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

    Neuronpedia

    INDEX
    Explanations

    wear and tear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ώς
    0.42
     '${
    0.41
     RasterModelGrid
    0.40
     পুনরায়
    0.39
     "\"
    0.38
    Ք
    0.38
    引领
    0.37
    ថ្
    0.37
    oğlu
    0.37
     endoscopic
    0.36
    POSITIVE LOGITS
     soci
    0.43
     Polit
    0.43
    即可
    0.42
     Stats
    0.42
     Bí
    0.41
     polit
    0.39
    Change
    0.39
     strat
    0.39
     Billy
    0.38
     ساع
    0.38
    Act Density 0.001%

    No Known Activations