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

    Neuronpedia

    INDEX
    Explanations

    FX

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jan
    -0.08
    Jan
    -0.07
    ennifer
    -0.07
     Tabs
    -0.07
     contradictory
    -0.06
    Vertex
    -0.06
    -grid
    -0.06
     birds
    -0.06
    greSQL
    -0.06
    scriptions
    -0.06
    POSITIVE LOGITS
     بع
    0.07
    Israeli
    0.06
    FX
    0.06
     Ahmed
    0.06
     ок
    0.06
     существ
    0.06
     FX
    0.06
     Vý
    0.06
    Russian
    0.06
     食
    0.06
    Act Density 0.003%

    No Known Activations