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

    Neuronpedia

    INDEX
    Explanations

    exceptions and considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     당연
    0.46
    当然
    0.45
     ovviamente
    0.44
     طبعا
    0.43
     natuurlijk
    0.43
    當然
    0.43
     естественно
    0.41
    ല്ലോ
    0.41
     évidemment
    0.40
     delimiter
    0.40
    POSITIVE LOGITS
     செய்தால்
    0.51
     Considering
    0.48
     considerar
    0.48
     considering
    0.46
     vooral
    0.45
     sobretudo
    0.45
     bør
    0.45
     cautiously
    0.45
    considering
    0.44
     Needs
    0.44
    Act Density 0.002%

    No Known Activations