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

    Neuronpedia

    INDEX
    Explanations

    "Sự"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suscit
    0.41
    类别
    0.41
    ปล
    0.40
    تمي
    0.40
     سسٹم
    0.40
    semantics
    0.39
     бясплат
    0.39
    міністра
    0.39
    льним
    0.39
    ליך
    0.38
    POSITIVE LOGITS
     truth
    0.43
     gum
    0.39
     colorful
    0.37
     possess
    0.37
     soc
    0.36
    Gun
    0.36
    ாடி
    0.36
     Gun
    0.35
     sở
    0.35
     saúde
    0.35
    Act Density 0.001%

    No Known Activations