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

    Neuronpedia

    INDEX
    Explanations

    Selenium code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sunrise
    -0.08
     assemble
    -0.07
     Meet
    -0.07
     Women
    -0.07
     approves
    -0.07
     acqu
    -0.07
     Product
    -0.06
    aland
    -0.06
    也是非常
    -0.06
     Darling
    -0.06
    POSITIVE LOGITS
     нарушен
    0.08
     coercion
    0.08
     chunks
    0.07
    造成
    0.07
    ıp
    0.07
     caching
    0.07
     legendary
    0.07
    ashtra
    0.07
     necessary
    0.07
    ış
    0.07
    Act Density 0.006%

    No Known Activations