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

    Neuronpedia

    INDEX
    Explanations

    Regular expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    我们就
    -0.08
     libertarian
    -0.08
    ields
    -0.07
     Demon
    -0.07
     Sell
    -0.07
    warm
    -0.07
     }.
    -0.07
     kilomet
    -0.07
    	puts
    -0.07
     Lawyers
    -0.07
    POSITIVE LOGITS
    Circle
    0.08
    FK
    0.07
    ethylene
    0.07
    牛奶
    0.07
     acrylic
    0.06
    쑤
    0.06
    叽
    0.06
     adresse
    0.06
     гр
    0.06
    php
    0.06
    Act Density 0.038%

    No Known Activations