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

    Neuronpedia

    INDEX
    Explanations

    building blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺖ
    0.93
     períodos
    0.90
     промышлен
    0.79
     النها
    0.77
    стный
    0.77
     цветов
    0.75
     другой
    0.74
     заканчи
    0.74
    [\
    0.74
     bzw
    0.72
    POSITIVE LOGITS
     carbohydrates
    0.83
     backpacks
    0.75
    του
    0.74
     booking
    0.73
     Booking
    0.73
    ariş
    0.73
     roses
    0.73
     pesticides
    0.72
    盔
    0.71
     Boxing
    0.70
    Act Density 0.000%

    No Known Activations