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

    Neuronpedia

    INDEX
    Explanations

    average and median age

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     can
    0.41
     wisely
    0.36
     medicinal
    0.34
    チャンス
    0.33
     কিনতে
    0.33
    Interrupt
    0.32
    可以
    0.32
     disk
    0.32
     можете
    0.32
    Captain
    0.32
    POSITIVE LOGITS
     평균
    0.64
    median
    0.64
    平均
    0.63
     median
    0.62
    mean
    0.59
    年齢
    0.59
    average
    0.56
     demographics
    0.56
     平均
    0.56
     उम्र
    0.56
    Act Density 0.018%

    No Known Activations