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

    Neuronpedia

    INDEX
    Explanations

    dessert recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     материал
    -0.07
     aray
    -0.07
    INGS
    -0.07
     JScrollPane
    -0.06
     RAF
    -0.06
     backups
    -0.06
    ICLES
    -0.06
     للم
    -0.06
    Performance
    -0.06
    217
    -0.06
    POSITIVE LOGITS
     sont
    0.06
     бі
    0.06
     assist
    0.06
     나를
    0.06
    bolt
    0.06
     hit
    0.06
    	atomic
    0.06
    rait
    0.06
     wallet
    0.06
     potent
    0.06
    Act Density 0.024%

    No Known Activations