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

    Neuronpedia

    INDEX
    Explanations

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شفنا
    0.37
     piacere
    0.37
    ゥ
    0.35
    лдуу
    0.35
    谠
    0.35
    ữu
    0.34
    ్రమ
    0.34
    漃
    0.34
     sıvı
    0.34
     kehad
    0.34
    POSITIVE LOGITS
    ในปี
    1.00
     vuonna
    0.96
     בשנת
    0.92
     circa
    0.85
    去年
    0.77
    கடந்த
    0.74
     October
    0.73
     கடந்த
    0.73
     February
    0.73
    昨年
    0.73
    Act Density 0.415%

    No Known Activations