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

    Neuronpedia

    INDEX
    Explanations

    months and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     както
    0.91
    場合に
    0.90
    是由
    0.88
    против
    0.86
    Зна
    0.85
     obje
    0.84
    א
    0.83
    穵
    0.83
     Größen
    0.82
    هایی
    0.81
    POSITIVE LOGITS
    1
    1.21
    2
    0.99
    7
    0.94
    下旬
    0.94
    9
    0.93
    3
    0.86
     மாதம்
    0.86
     onwards
    0.85
    4
    0.84
    6
    0.84
    Act Density 0.006%

    No Known Activations