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

    Neuronpedia

    INDEX
    Explanations

    real

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dos
    -0.09
     Offshore
    -0.09
     Fraud
    -0.09
     Administrator
    -0.08
    iseksi
    -0.08
     vart
    -0.08
     કાર્યક્રમ
    -0.08
     необходимые
    -0.08
     medewerker
    -0.08
     pisc
    -0.08
    POSITIVE LOGITS
    世界
    0.11
     दुनिया
    0.10
     reality
    0.09
     દુન
    0.09
     düny
    0.09
    -world
    0.09
    现实
    0.09
     realities
    0.09
     world
    0.09
    Category
    0.09
    Act Density 0.015%

    No Known Activations