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

    Neuronpedia

    INDEX
    Explanations

    historical centuries and eras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ྲ
    0.43
    以来
    0.40
    ccncc
    0.39
    日子
    0.35
    Depuis
    0.35
    Hiện
    0.35
    今日も
    0.35
     grandkids
    0.34
    வர்களும்
    0.34
    今年も
    0.34
    POSITIVE LOGITS
     nineteenth
    2.03
     seventeenth
    1.80
     eighteenth
    1.78
     Nineteenth
    1.70
     sixteenth
    1.60
     twentieth
    1.55
     Eighteenth
    1.55
     XIX
    1.52
     fifteenth
    1.46
     fourteenth
    1.44
    Act Density 0.028%

    No Known Activations