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

    Neuronpedia

    INDEX
    Explanations

    3-4 letter words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clesiastical
    0.48
    ുകളില്‍
    0.47
    ittarius
    0.46
    atherine
    0.45
    يني
    0.43
    >>>>>>>>
    0.43
    osion
    0.42
    apanicola
    0.42
    স্থানীয়
    0.42
    udarstven
    0.42
    POSITIVE LOGITS
     Ford
    0.43
     digits
    0.42
     aero
    0.41
     O
    0.40
     cabs
    0.39
     Benz
    0.39
    ਾ
    0.38
     Stress
    0.38
     View
    0.37
     可
    0.37
    Act Density 0.059%

    No Known Activations