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

    Neuronpedia

    INDEX
    Explanations

    years followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     February
    0.34
     فبراير
    0.32
     Hopefully
    0.32
     ragazzo
    0.30
     migliore
    0.30
     FEBRUARY
    0.29
     ফেব্রুয়ার
    0.29
     melhor
    0.28
     গত
    0.28
     ২০২৩
    0.28
    POSITIVE LOGITS
     silam
    0.52
     yılında
    0.37
    년에
    0.37
    년
    0.37
     году
    0.36
    年
    0.35
    년부터
    0.34
    ish
    0.34
    年的
    0.33
    年には
    0.33
    Act Density 0.028%

    No Known Activations