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

    Neuronpedia

    INDEX
    Explanations

    web design code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sunglasses
    -0.07
    磺
    -0.07
     amen
    -0.07
    废气
    -0.07
    uhe
    -0.06
     descent
    -0.06
     Dare
    -0.06
    gemäß
    -0.06
    +
    -0.06
    pure
    -0.06
    POSITIVE LOGITS
    把我
    0.08
     Tôi
    0.08
     أنا
    0.07
    把自己
    0.07
    ledon
    0.07
    当我们
    0.07
    Country
    0.07
     עכשיו
    0.07
     Ay
    0.07
    .cookies
    0.07
    Act Density 0.030%

    No Known Activations