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

    Neuronpedia

    INDEX
    Explanations

    refrigerator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     broom
    -0.08
    udet
    -0.07
    纷
    -0.07
     бич
    -0.07
    基金
    -0.07
    orris
    -0.07
     Move
    -0.07
     knowingly
    -0.07
     cement
    -0.07
     urs
    -0.07
    POSITIVE LOGITS
    Temperature
    0.08
     المحمول
    0.08
     منخفض
    0.08
    _temperature
    0.08
     Trucks
    0.08
     froid
    0.08
    housing
    0.08
     cold
    0.08
     temperature
    0.07
     refrigerator
    0.07
    Act Density 0.005%

    No Known Activations