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

    Neuronpedia

    INDEX
    Explanations

    under pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lying
    0.49
    liegt
    0.42
     /$
    0.41
     subheading
    0.41
    嶺
    0.41
     lying
    0.40
    itherto
    0.39
    liegen
    0.39
     heading
    0.39
    heading
    0.38
    POSITIVE LOGITS
     presión
    0.70
     pressure
    0.70
    压力
    0.64
     Pressure
    0.64
    Pressure
    0.57
     stress
    0.55
     दबाव
    0.55
     pressured
    0.55
     प्रेशर
    0.54
    压
    0.54
    Act Density 0.006%

    No Known Activations