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

    Neuronpedia

    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harold
    -0.07
    osaic
    -0.07
    _MT
    -0.06
     bereits
    -0.06
    External
    -0.06
    Ster
    -0.06
    --------------↵
    -0.06
    	message
    -0.06
     Estimated
    -0.06
     Leaving
    -0.06
    POSITIVE LOGITS
     Duterte
    0.07
     tho
    0.07
    abal
    0.07
     BEST
    0.06
     california
    0.06
     wn
    0.06
     movement
    0.06
    armac
    0.06
     카지노
    0.06
     sess
    0.06
    Act Density 0.005%

    No Known Activations