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

    Neuronpedia

    INDEX
    Explanations

    Pow followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    1.43
    ل
    1.35
    ۲
    1.34
    ۳
    1.27
    ด
    1.20
    ب
    1.20
    ב
    1.20
    (
    1.17
    し
    1.17
    ED
    1.16
    POSITIVE LOGITS
    zione
    1.09
    grounds
    1.02
     Сред
    1.01
    book
    1.00
     Συ
    1.00
    ğu
    0.98
     Ви
    0.96
    nae
    0.96
     الك
    0.95
    }}
    0.95
    Act Density 0.000%

    No Known Activations