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

    Neuronpedia

    INDEX
    Explanations

    Technologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shove
    -0.06
    овор
    -0.06
     города
    -0.06
    EST
    -0.06
     EOS
    -0.06
    (out
    -0.06
     bargaining
    -0.06
     regard
    -0.06
     raz
    -0.06
     vouchers
    -0.06
    POSITIVE LOGITS
    ())↵↵↵
    0.07
    says
    0.07
     والتي
    0.06
     sendData
    0.06
    icens
    0.06
    +-
    0.06
     drafted
    0.06
     –↵↵
    0.06
     ];
    0.06
    Để
    0.06
    Act Density 0.001%

    No Known Activations