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

    Neuronpedia

    INDEX
    Explanations

    blue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Compile
    -0.06
    ए
    -0.06
    orbit
    -0.06
     호
    -0.06
     Historic
    -0.06
    Pair
    -0.06
     leaks
    -0.06
    ars
    -0.06
    ад
    -0.06
     Independence
    -0.06
    POSITIVE LOGITS
     submissive
    0.07
    ，是
    0.07
    .getMin
    0.07
     sne
    0.07
    으면
    0.06
    Seattle
    0.06
    (Texture
    0.06
    leme
    0.06
     sitting
    0.06
     الأ
    0.06
    Act Density 0.005%

    No Known Activations