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

    Neuronpedia

    INDEX
    Explanations

    impossibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pixels
    -0.07
     animated
    -0.06
     SHE
    -0.06
     HDD
    -0.06
     Pell
    -0.06
     EAST
    -0.06
     Shelby
    -0.06
     kterých
    -0.06
     pract
    -0.06
     breat
    -0.06
    POSITIVE LOGITS
     بالم
    0.08
     posed
    0.07
    rai
    0.06
    '])->
    0.06
    inant
    0.06
    vature
    0.06
     Spinner
    0.06
     tö
    0.06
    ประสบ
    0.06
    ahat
    0.06
    Act Density 0.138%

    No Known Activations