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

    Neuronpedia

    INDEX
    Explanations

    consumer reviews on google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potato
    0.49
     tunnel
    0.45
     zu
    0.44
     billowing
    0.44
     destroyed
    0.43
     destroying
    0.42
     destroy
    0.41
     env
    0.41
     epile
    0.41
     quantization
    0.41
    POSITIVE LOGITS
     Consumer
    0.84
    consumer
    0.84
     consumer
    0.84
    Consumer
    0.78
     потреби
    0.77
    消费者
    0.77
     소비자
    0.75
    consumers
    0.71
     Consumers
    0.70
     consumers
    0.69
    Act Density 0.023%

    No Known Activations