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

    Neuronpedia

    INDEX
    Explanations

    options or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elő
    0.51
     restrained
    0.50
     상당
    0.49
     égard
    0.48
    ენა
    0.48
     bardziej
    0.47
     MDLVertex
    0.47
     setToDefault
    0.46
    лена
    0.46
    த்துக்கும்
    0.46
    POSITIVE LOGITS
    Boris
    0.45
    Sib
    0.44
    Chuck
    0.44
     globalization
    0.44
    il
    0.43
    Sales
    0.42
     نړۍ
    0.42
     Sä
    0.42
    Manufacturing
    0.41
     fonts
    0.41
    Act Density 0.002%

    No Known Activations