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

    Neuronpedia

    INDEX
    Explanations

    years old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     นึง
    0.41
     なく
    0.38
    fcast
    0.38
    iamine
    0.37
     décadas
    0.37
    较低
    0.37
     Longer
    0.37
     архив
    0.37
    iamy
    0.36
     زمن
    0.36
    POSITIVE LOGITS
     old
    2.14
    old
    1.77
    Old
    1.48
     olds
    1.45
     Old
    1.38
     OLD
    1.35
    旧
    1.34
    OLD
    1.31
    老
    1.30
     পুরনো
    1.28
    Act Density 0.017%

    No Known Activations