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

    Neuronpedia

    INDEX
    Explanations

    page

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modified
    -0.08
     paralle
    -0.08
     purposes
    -0.07
    누
    -0.07
     liquide
    -0.07
     cura
    -0.07
     ex
    -0.07
    建
    -0.07
     undertaken
    -0.07
    .counter
    -0.07
    POSITIVE LOGITS
     المنافس
    0.10
     ಸ್ಥಾನ
    0.09
     retailer
    0.09
    以内
    0.08
     CNBC
    0.08
     ESPN
    0.08
    نافس
    0.08
    wynt
    0.08
     coveted
    0.08
     نتائج
    0.08
    Act Density 0.007%

    No Known Activations