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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thao
    -0.07
     antigen
    -0.07
     mensen
    -0.07
     invasion
    -0.06
    	location
    -0.06
     motivate
    -0.06
     Ley
    -0.06
     해야
    -0.06
     wrappers
    -0.06
     imkan
    -0.06
    POSITIVE LOGITS
    .extent
    0.08
    .fastjson
    0.07
    (beta
    0.07
    (sender
    0.06
     Carpenter
    0.06
     ypos
    0.06
     epidemi
    0.06
    ----------
↵
    0.06
    .defer
    0.06
    _plugins
    0.06
    Act Density 0.019%

    No Known Activations