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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    dates as numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.77
    ла
    0.56
    ే
    0.54
    ת
    0.52
    و
    0.48
    ו
    0.48
    ed
    0.44
    ت
    0.44
    ل
    0.43
    er
    0.42
    POSITIVE LOGITS
    0.44
     a
    0.44
     are
    0.41
    {
    0.41
    ется
    0.35
    ிகள்
    0.34
    <
    0.33
    \
    0.33
    asi
    0.33
     an
    0.32
    Act Density 0.000%

    No Known Activations