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

    Neuronpedia

    INDEX
    Explanations

    12

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	padding
    -0.07
     устра
    -0.06
     compat
    -0.06
    genome
    -0.06
     नक
    -0.06
     shading
    -0.06
     اخت
    -0.06
     поба
    -0.06
    sak
    -0.06
     Schwartz
    -0.06
    POSITIVE LOGITS
    12
    0.11
    012
    0.09
     "_
    0.08
    712
    0.08
     未
    0.08
    121
    0.07
    762
    0.07
    elfth
    0.07
     Oliver
    0.07
    912
    0.07
    Act Density 0.070%

    No Known Activations