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

    Neuronpedia

    INDEX
    Explanations

    Palmer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dk
    -0.07
     kön
    -0.07
     ย
    -0.06
     Boris
    -0.06
     Cla
    -0.06
    god
    -0.06
     tog
    -0.06
    	j
    -0.06
     의미
    -0.06
    analyze
    -0.06
    POSITIVE LOGITS
    /U
    0.07
     Walton
    0.07
     operator
    0.06
    ALSE
    0.06
     Covid
    0.06
     operators
    0.06
    LOUR
    0.06
    임
    0.06
     colleague
    0.06
     transformation
    0.06
    Act Density 0.001%

    No Known Activations