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

    Neuronpedia

    INDEX
    Explanations

    average and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cantidad
    0.47
    Occurrence
    0.45
    Amount
    0.44
     Specifies
    0.43
    AMOUNT
    0.43
    ológicos
    0.42
     basilaires
    0.41
    modification
    0.41
     Occurrence
    0.40
     максимум
    0.40
    POSITIVE LOGITS
     average
    0.93
     평균
    0.83
    平均
    0.80
    average
    0.79
     avg
    0.77
     gemidd
    0.75
     averages
    0.71
    avg
    0.68
     Average
    0.68
    Average
    0.68
    Act Density 0.009%

    No Known Activations