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

    Neuronpedia

    INDEX
    Explanations

    python application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेत
    1.00
     vuole
    0.97
     	i
    0.96
     riguard
    0.95
    ərbaycan
    0.94
    ちは
    0.94
     riguarda
    0.92
    geschoss
    0.92
     phận
    0.91
     demás
    0.89
    POSITIVE LOGITS
    т
    1.64
    й
    1.41
     Kyr
    1.20
    ي
    1.18
    ی
    1.15
    जफ्
    1.14
    י
    1.14
    ikal
    1.14
    на
    1.13
    दर
    1.12
    Act Density 0.106%

    No Known Activations