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

    Neuronpedia

    INDEX
    Explanations

    joke

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kud
    -0.09
     worthy
    -0.08
     transpl
    -0.08
     Bram
    -0.08
     Chelsea
    -0.08
    \Input
    -0.08
     Heads
    -0.08
    �
    -0.08
     Witt
    -0.07
     rnd
    -0.07
    POSITIVE LOGITS
     besteden
    0.07
    Recovery
    0.07
    െയുള്ള
    0.07
     respiration
    0.07
     платить
    0.07
     basta
    0.07
     herstellen
    0.07
    ’ll
    0.06
    Buffered
    0.06
     Dauer
    0.06
    Act Density 0.002%

    No Known Activations