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

    Neuronpedia

    INDEX
    Explanations

    runner's high or runner-up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    2.01
    fully
    1.95
    ти
    1.83
    ą
    1.76
    र
    1.72
    म
    1.71
    면
    1.68
    ্রি
    1.68
     profusely
    1.67
    ع
    1.67
    POSITIVE LOGITS
    ActivityCompat
    2.04
    ه
    2.01
    aquest
    1.98
    د
    1.92
    o
    1.86
     toen
    1.85
     Asimismo
    1.85
     Tories
    1.84
    Основ
    1.83
    ю
    1.81
    Act Density 0.001%

    No Known Activations