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

    Neuronpedia

    INDEX
    Explanations

    capture or calculate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Insurance
    0.46
    Insurance
    0.43
    ეგი
    0.42
    Listing
    0.41
     equation
    0.41
    विष्ट
    0.40
    保险
    0.40
    信任
    0.40
    鹬
    0.39
    辔
    0.39
    POSITIVE LOGITS
     unsere
    0.54
     لكن
    0.52
    culares
    0.50
     ausges
    0.50
     grundsätzlich
    0.49
    foundland
    0.49
    nemen
    0.49
     précise
    0.48
     bringen
    0.47
     പക്ഷേ
    0.47
    Act Density 0.002%

    No Known Activations