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

    Neuronpedia

    INDEX
    Explanations

    sentiment analysis and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原来
    0.86
    原來
    0.77
     sogenannte
    0.75
     või
    0.70
     문제입니다
    0.69
    ajo
    0.68
     scared
    0.67
     insieme
    0.67
     kostet
    0.66
     或者
    0.66
    POSITIVE LOGITS
     descriptions
    1.30
     classifications
    1.16
     prices
    1.15
     information
    1.11
    descriptions
    1.09
    prices
    1.08
     percentages
    1.07
     interpretations
    1.06
     ':'
    1.02
    Percentages
    1.00
    Act Density 0.503%

    No Known Activations