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

    Neuronpedia

    INDEX
    Explanations

    gratitude and thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     예측
    0.78
     판단
    0.76
     predictive
    0.74
     prediction
    0.72
     dandruff
    0.72
     epithelium
    0.70
     behaves
    0.70
     violation
    0.70
     elast
    0.69
     deflection
    0.69
    POSITIVE LOGITS
     gratitude
    1.57
     grateful
    1.55
    grateful
    1.49
     gratefully
    1.39
     thankful
    1.36
     thanked
    1.34
     благодар
    1.30
    感謝
    1.26
     thanking
    1.26
     agradecer
    1.25
    Act Density 0.037%

    No Known Activations