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

    Neuronpedia

    INDEX
    Explanations

    loan words and international terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perceptive
    0.29
     évaluations
    0.29
     ключе
    0.29
     comedic
    0.28
     үч
    0.28
     harrowing
    0.28
     opción
    0.27
     deutlich
    0.27
     temsil
    0.27
     kapsamında
    0.27
    POSITIVE LOGITS
    ↵
    0.33
    ש
    0.32
     liquors
    0.29
    чики
    0.29
    وانات
    0.29
     gardens
    0.28
    植物
    0.28
     plants
    0.28
    вання
    0.28
    ган
    0.28
    Act Density 0.040%

    No Known Activations