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

    Neuronpedia

    INDEX
    Explanations

    color descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Team
    -0.08
    -Pacific
    -0.08
    四大
    -0.07
    Ros
    -0.06
     rotor
    -0.06
    .Override
    -0.06
    顆
    -0.06
    ())
↵
    -0.06
    	de
    -0.06
    nicos
    -0.06
    POSITIVE LOGITS
    改装
    0.07
     Gł
    0.07
    默认
    0.07
    'LBL
    0.07
     Hutch
    0.07
     наз
    0.07
     Fix
    0.06
     authenticate
    0.06
     breakthrough
    0.06
     ebay
    0.06
    Act Density 0.066%

    No Known Activations