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

    Neuronpedia

    INDEX
    Explanations

    where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಏನ
    0.75
     glance
    0.70
     bus
    0.70
     CLUB
    0.69
     понравилось
    0.68
     club
    0.67
     Club
    0.67
     tram
    0.67
     baby
    0.63
    rofoam
    0.63
    POSITIVE LOGITS
     where
    2.35
    where
    2.22
    Where
    2.09
     Where
    2.06
     где
    1.99
    其中
    1.97
     donde
    1.91
     其中
    1.89
     où
    1.85
     gdzie
    1.75
    Act Density 0.197%

    No Known Activations