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

    Neuronpedia

    INDEX
    Explanations

    proper one option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     χρησιμοποι
    0.98
     troviamo
    0.90
     пі
    0.85
     risol
    0.83
     створення
    0.83
     прадстаў
    0.83
    Фі
    0.83
     використову
    0.82
     літоў
    0.82
     ഉപയോഗ
    0.82
    POSITIVE LOGITS
    1.16
    ；
    0.87
    ，
    0.83
    ！
    0.82
    ：
    0.75
    －
    0.74
    ？
    0.73
    ＆
    0.73
     cooperated
    0.72
     Xinhua
    0.72
    Act Density 0.001%

    No Known Activations