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

    Neuronpedia

    INDEX
    Explanations

    argument parsing, argparse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     والدہ
    0.45
    خواندن
    0.41
    ம்தா
    0.41
    raag
    0.41
    ptide
    0.41
     lapangan
    0.40
     ورځې
    0.40
     ننوت
    0.40
    ថ្ងៃ
    0.38
    迵
    0.37
    POSITIVE LOGITS
     type
    0.79
    type
    0.61
     Met
    0.57
     Type
    0.56
     dest
    0.55
     action
    0.55
     Dest
    0.54
     metavar
    0.54
     choices
    0.50
     τύ
    0.49
    Act Density 0.001%

    No Known Activations