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

    Neuronpedia

    INDEX
    Explanations

    superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overall
    0.47
     Multiplayer
    0.44
     fewer
    0.40
     irgendwo
    0.39
    лович
    0.38
     actuel
    0.38
     lvl
    0.37
     It
    0.37
     THEIR
    0.37
    ==
    0.36
    POSITIVE LOGITS
     tini
    0.74
     imaginable
    0.72
     slightest
    0.63
     cutest
    0.54
     wildest
    0.53
    最
    0.53
     smallest
    0.52
     самых
    0.51
     conceivable
    0.50
     ಅತ್ಯ
    0.49
    Act Density 0.027%

    No Known Activations