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

    Neuronpedia

    INDEX
    Explanations

    family relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تحسين
    -0.08
     иннова
    -0.08
     afwijk
    -0.08
    ’efficacité
    -0.08
     moneda
    -0.08
     ASTM
    -0.07
    ั่ง
    -0.07
     तेज
    -0.07
    /pdf
    -0.07
     diode
    -0.07
    POSITIVE LOGITS
     spouse
    0.15
     spouses
    0.14
     roommates
    0.14
     grandparents
    0.14
     nieces
    0.12
     siblings
    0.12
     relatives
    0.12
     parents
    0.12
     classmates
    0.11
    兄
    0.11
    Act Density 0.015%

    No Known Activations