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

    Neuronpedia

    INDEX
    Explanations

    emphasizing or listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ždy
    0.45
     മാത്രമല്ല
    0.43
     అందుకే
    0.43
    轻易
    0.43
    简直
    0.42
    ર્સ
    0.42
    ygons
    0.41
    rase
    0.41
    ysa
    0.41
     তাক
    0.41
    POSITIVE LOGITS
     Meanwhile
    0.44
     grop
    0.42
     intermittently
    0.40
     and
    0.39
     Sediment
    0.39
     clar
    0.39
     confusión
    0.38
     Prima
    0.38
     sugger
    0.38
     \
    0.37
    Act Density 0.027%

    No Known Activations