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

    Neuronpedia

    INDEX
    Explanations

    Programming code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    武警
    -0.07
    年开始
    -0.07
    JNIEXPORT
    -0.07
     Midwest
    -0.07
     gerekt
    -0.07
     Southern
    -0.07
    Smarty
    -0.07
     tan
    -0.07
    %timeout
    -0.07
     Ratio
    -0.07
    POSITIVE LOGITS
     kitchens
    0.07
    reviews
    0.07
    direccion
    0.07
     prof
    0.07
    subscriber
    0.06
    就被
    0.06
    -graph
    0.06
     PLAY
    0.06
     Select
    0.06
     privat
    0.06
    Act Density 0.143%

    No Known Activations