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

    Neuronpedia

    INDEX
    Explanations

    consumer reports and reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Consumer
    0.61
     consumer
    0.60
    Consumer
    0.58
    consumer
    0.57
     потреби
    0.57
    消費
    0.54
    消费
    0.52
     소비자
    0.49
    消费者
    0.49
     Verbrauch
    0.43
    POSITIVE LOGITS
    predict
    0.44
     prediction
    0.43
     punitive
    0.43
     illness
    0.42
     tela
    0.42
    ಕ್ರಮ
    0.42
     resin
    0.42
     health
    0.41
     predict
    0.41
    feitura
    0.41
    Act Density 0.001%

    No Known Activations