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

    Neuronpedia

    INDEX
    Explanations

    allocating memory buckets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.42
    lingu
    0.41
    ள்ளார்
    0.40
     designer
    0.40
    A
    0.40
    oulis
    0.39
    ѕ
    0.39
    asta
    0.37
    s
    0.37
     mobil
    0.37
    POSITIVE LOGITS
    ン
    0.61
     treaties
    0.52
     öğrend
    0.48
    ურთიერთ
    0.47
     ły
    0.47
    教程
    0.46
     compartilh
    0.46
     Heter
    0.44
     Nội
    0.44
    0.43
    Act Density 0.000%

    No Known Activations