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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Faction
    -0.07
     později
    -0.06
     snapshots
    -0.06
     that
    -0.06
     cận
    -0.06
    entar
    -0.06
    вает
    -0.06
     вол
    -0.06
     تواند
    -0.06
     Diamonds
    -0.06
    POSITIVE LOGITS
    callable
    0.07
     functioning
    0.07
      ↵↵
    0.07
    553
    0.07
    "}
    0.06
    .closed
    0.06
    Same
    0.06
     yrs
    0.06
    332
    0.06
    km
    0.06
    Act Density 0.010%

    No Known Activations