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

    Neuronpedia

    INDEX
    Explanations

    teaching them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    인의
    0.93
    ার্থীর
    0.91
     প্রতিনিধ
    0.88
     உலகின்
    0.86
    원의
    0.85
     extraordinarily
    0.84
    šķ
    0.82
    ِ
    0.81
    ائِ
    0.79
     මෙම
    0.78
    POSITIVE LOGITS
     Both
    0.99
     Lady
    0.98
     Tutti
    0.93
     Everyone
    0.92
     Ella
    0.92
     everyone
    0.91
     Meanwhile
    0.90
     Tous
    0.88
     остальные
    0.87
     Serena
    0.87
    Act Density 0.039%

    No Known Activations