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

    Neuronpedia

    INDEX
    Explanations

    counting things with SQL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     averaging
    0.53
    平均
    0.49
     averaged
    0.47
     平均
    0.47
     averages
    0.43
     প্রতিটি
    0.43
     gemidd
    0.41
     Increasing
    0.41
     average
    0.40
    averaged
    0.40
    POSITIVE LOGITS
    count
    0.72
     COUNT
    0.71
    カウント
    0.69
     count
    0.68
     Count
    0.66
    Count
    0.66
    COUNT
    0.63
    Counts
    0.60
    counts
    0.58
     counted
    0.58
    Act Density 0.031%

    No Known Activations