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

    Neuronpedia

    INDEX
    Explanations

    ```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    សម្រាប់ការ
    1.13
    на
    1.08
    િ
    0.92
    សម្រាប់
    0.89
    อื่น
    0.88
    ဍ
    0.88
    ті
    0.87
    ларды
    0.86
    Makanan
    0.84
     संग्रहालय
    0.84
    POSITIVE LOGITS
    '
    1.31
    ()
    1.13
    :
    1.06
     unveils
    1.05
    4
    1.05
    ',
    1.04
     it
    1.02
    ,
    1.02
     this
    1.01
     :
    1.01
    Act Density 0.118%

    No Known Activations