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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     सीट
    -0.08
     נכון
    -0.08
     sân
    -0.08
     vouloir
    -0.08
    	best
    -0.08
     होटल
    -0.08
     Seats
    -0.08
     공연
    -0.07
    Ticket
    -0.07
    	write
    -0.07
    POSITIVE LOGITS
     echar
    0.09
    -Friendly
    0.08
    ably
    0.08
     easily
    0.08
    -cut
    0.08
     understandable
    0.08
    -friendly
    0.08
     Darstellung
    0.08
     facilement
    0.07
    kv
    0.07
    Act Density 0.009%

    No Known Activations