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

    Neuronpedia

    INDEX
    Explanations

    much or lot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     awareness
    0.48
     relev
    0.46
     relevance
    0.46
     knowledge
    0.45
     need
    0.42
     expertise
    0.42
     flexibility
    0.41
     variation
    0.40
     visibility
    0.39
     puzz
    0.39
    POSITIVE LOGITS
     జరిగిన
    0.46
    }}$;
    0.42
    ່ງ
    0.42
     yoğun
    0.42
    痨
    0.42
     நடந்த
    0.41
     дерев
    0.39
    ಿಸಿದ
    0.39
    handled
    0.38
     читать
    0.37
    Act Density 0.006%

    No Known Activations