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

    Neuronpedia

    INDEX
    Explanations

    you/your/love/relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     usamos
    0.46
     कराना
    0.45
    аз
    0.44
     obviously
    0.42
     encoders
    0.42
     dispensers
    0.41
    Grp
    0.40
     обеспечения
    0.40
     списке
    0.40
     உற்ப
    0.39
    POSITIVE LOGITS
     તમારે
    0.59
    恋
    0.53
     שלך
    0.52
     youll
    0.52
     તમારા
    0.51
     ನಿಮ್ಮ
    0.50
     votre
    0.50
    你的
    0.49
    💑
    0.49
    Votre
    0.48
    Act Density 0.033%

    No Known Activations