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

    Neuronpedia

    INDEX
    Explanations

    an adequate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     considerado
    0.97
     popraw
    0.95
    ندا
    0.89
     мод
    0.87
     страницы
    0.86
     dành
    0.86
     Nachricht
    0.86
     kalangan
    0.85
     ሴ
    0.85
     ώστε
    0.85
    POSITIVE LOGITS
     frequently
    1.01
     salons
    0.96
     halves
    0.94
    aks
    0.94
    篷
    0.94
     pines
    0.93
     payouts
    0.93
     axles
    0.92
    ϳ
    0.91
    unately
    0.90
    Act Density 0.000%

    No Known Activations