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

    Neuronpedia

    INDEX
    Explanations

    Icelandic place names and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cher
    0.73
     beque
    0.72
     आजम
    0.69
    ेक्ट
    0.69
    ख
    0.68
     Dense
    0.66
     Conver
    0.65
     Oracle
    0.65
    Oracle
    0.65
     reverse
    0.64
    POSITIVE LOGITS
     þ
    1.40
     með
    1.31
     í
    1.30
    ð
    1.30
     Í
    1.28
     að
    1.27
     við
    1.26
    ið
    1.23
     Þ
    1.23
     á
    1.22
    Act Density 0.024%

    No Known Activations