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

    Neuronpedia

    INDEX
    Explanations

    Dane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    1.58
    )
    1.52
    ang
    1.27
    er
    1.23
    اتی
    1.23
    го
    1.19
    نگ
    1.13
    ]
    1.11
    t
    1.10
    อร์
    0.99
    POSITIVE LOGITS
     في
    1.83
     в
    1.62
     to
    1.59
    ير
    1.53
     ي
    1.41
     الك
    1.38
     بسي
    1.33
     وي
    1.29
    ية
    1.28
     بي
    1.28
    Act Density 0.000%

    No Known Activations