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

    Neuronpedia

    INDEX
    Explanations

    sont

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    释
    -0.07
     around
    -0.06
     Volume
    -0.06
     Gu
    -0.06
     Cobra
    -0.06
     Dé
    -0.06
    透
    -0.06
     electronically
    -0.06
     qb
    -0.06
     utiliz
    -0.06
    POSITIVE LOGITS
     sont
    0.30
    taient
    0.11
     étaient
    0.10
     seront
    0.10
     sunt
    0.08
    -centric
    0.08
    @Service
    0.08
    سات
    0.08
     bringen
    0.07
    	animation
    0.07
    Act Density 0.002%

    No Known Activations