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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bespoke
    0.47
    0.37
    ‌
    0.36
    £
    0.35
    _
    0.34
     superb
    0.34
     summarise
    0.34
     Sự
    0.34
     Modelling
    0.33
    ä
    0.33
    POSITIVE LOGITS
     headlights
    0.59
     tires
    0.56
     véhicules
    0.55
    エンジン
    0.54
     السيارة
    0.54
     neumáticos
    0.53
     gasoline
    0.52
     carburetor
    0.50
     wheelchairs
    0.50
     গাড়ীতে
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.