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

    Neuronpedia

    INDEX
    Explanations

    pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.18
    し
    1.18
    ود
    1.03
     It
    1.02
    ır
    1.02
    ใน
    1.00
    ین
    0.95
    ма
    0.89
    ه‌های
    0.86
    在
    0.86
    POSITIVE LOGITS
    ↵↵
    1.55
    us
    1.53
     pressure
    1.25
    ن
    1.19
    ع
    1.17
    ing
    1.13
    5
    1.13
    ли
    1.09
    al
    1.08
    Pressure
    1.07
    Act Density 0.027%

    No Known Activations