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

    Neuronpedia

    INDEX
    Explanations

    years, seconds, or centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nantinya
    0.17
     Day
    0.17
     শেখ
    0.16
    দির
    0.16
     Time
    0.16
    ات
    0.16
    aminen
    0.16
    itemize
    0.16
    时不
    0.16
     Version
    0.16
    POSITIVE LOGITS
     onwards
    0.27
     onward
    0.26
     ago
    0.21
     because
    0.19
     when
    0.19
    부터
    0.18
     vì
    0.18
     când
    0.17
     rekind
    0.17
    ₽
    0.17
    Act Density 0.045%

    No Known Activations