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

    Neuronpedia

    INDEX
    Explanations

    robot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    URATION
    -0.09
     secreto
    -0.08
     deutlich
    -0.08
     suyo
    -0.08
     səb
    -0.08
     subi
    -0.08
    arà
    -0.08
     bilder
    -0.08
     vorgenommen
    -0.08
     ক্ষেত্রে
    -0.08
    POSITIVE LOGITS
    -assisted
    0.08
     kitchen
    0.08
     concierge
    0.08
    厨
    0.08
     привет
    0.08
     Matt
    0.08
     kitchens
    0.08
     Kitchen
    0.08
     chef
    0.08
    -certified
    0.08
    Act Density 0.007%

    No Known Activations