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

    Neuronpedia

    INDEX
    Explanations

    Reversing an action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coch
    -0.08
     farming
    -0.08
     chunk
    -0.08
     Lin
    -0.07
     фон
    -0.07
     Farming
    -0.07
     farmac
    -0.07
     mathematic
    -0.07
     fühl
    -0.07
     conclusão
    -0.07
    POSITIVE LOGITS
    unlikely
    0.09
     Und
    0.09
     qaar
    0.08
     nond
    0.08
     possibility
    0.08
     existed
    0.08
    MENU
    0.07
    Und
    0.07
     sementara
    0.07
    [email
    0.07
    Act Density 0.025%

    No Known Activations