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

    Neuronpedia

    INDEX
    Explanations

    inference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ejemplo
    -0.07
    malar
    -0.07
     punk
    -0.07
     команди
    -0.07
     перш
    -0.06
     proto
    -0.06
     rewriting
    -0.06
     Sist
    -0.06
    едини
    -0.06
     disparity
    -0.06
    POSITIVE LOGITS
     UNITED
    0.07
    isAdmin
    0.07
     ओर
    0.06
    今日
    0.06
    กราคม
    0.06
    +Sans
    0.06
    :)];↵
    0.06
     nigeria
    0.06
     يناير
    0.06
    oldt
    0.06
    Act Density 0.002%

    No Known Activations