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

    Neuronpedia

    INDEX
    Explanations

    parentheses and asterisks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ViewPager
    -0.07
     diplomatic
    -0.07
     땅
    -0.06
     Recipe
    -0.06
    Third
    -0.06
    .circle
    -0.06
     Broadcasting
    -0.06
     third
    -0.06
     borderTop
    -0.06
     Mongo
    -0.06
    POSITIVE LOGITS
    езульт
    0.07
     petite
    0.07
     tetas
    0.06
     Senators
    0.06
     fraud
    0.06
     ním
    0.06
    (EFFECT
    0.06
     ответствен
    0.06
    very
    0.06
    getattr
    0.06
    Act Density 0.026%

    No Known Activations