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

    Neuronpedia

    INDEX
    Explanations

    high returns or yields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.51
    А
    0.49
    чей
    0.47
    kons
    0.47
    א
    0.47
     reeds
    0.46
    З
    0.44
    กก
    0.44
     intertwined
    0.44
     kompakt
    0.43
    POSITIVE LOGITS
     रिएक्टर
    0.48
     खपत
    0.47
    ).$$
    0.46
     ﺍﻟ
    0.46
    localVar
    0.46
     McNeil
    0.46
     phương
    0.45
    世紀
    0.45
     Judiciary
    0.45
     Tripoli
    0.45
    Act Density 0.002%

    No Known Activations