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

    Neuronpedia

    INDEX
    Explanations

    Q3, pari, 75%

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polytopes
    0.34
     handicrafts
    0.33
     healthful
    0.32
     mâles
    0.31
    रिडोर
    0.31
     oportunidad
    0.30
     gastronom
    0.30
     annealing
    0.29
     taxon
    0.29
     cropland
    0.29
    POSITIVE LOGITS
    However
    0.32
    &
    0.31
    abb
    0.31
    In
    0.31
    0.31
    in
    0.31
    the
    0.31
    Unfortunately
    0.31
    ua
    0.30
    only
    0.30
    Act Density 0.243%

    No Known Activations