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

    Neuronpedia

    INDEX
    Explanations

    code markers and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wikipedia
    0.58
    Browse
    0.56
    formerly
    0.55
     théâtre
    0.54
    wat
    0.53
    купки
    0.53
     leçon
    0.52
    subscription
    0.52
     signalé
    0.52
    ਾਈ
    0.51
    POSITIVE LOGITS
     மாட்ட
    0.59
     suppressant
    0.48
     =
    0.47
    ρύ
    0.45
     ans
    0.44
     &
    0.43
     ઓ
    0.43
    ेंट्स
    0.43
     स
    0.42
    /
    0.42
    Act Density 0.053%

    No Known Activations