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

    Neuronpedia

    INDEX
    Explanations

    inner layer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     всі
    0.67
     sleepers
    0.66
    𝐠
    0.65
    णाऱ्या
    0.65
     coarsely
    0.64
    爆发
    0.64
    emiz
    0.64
    াহিয়া
    0.62
    ल्ल्या
    0.62
     पीएफआई
    0.62
    POSITIVE LOGITS
     também
    0.83
     also
    0.81
     тоже
    0.80
     también
    0.78
    also
    0.77
     również
    0.77
     также
    0.73
     tiež
    0.72
     cũng
    0.71
     hingegen
    0.71
    Act Density 1.271%

    No Known Activations