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

    Neuronpedia

    INDEX
    Explanations

    percentage of total

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     majority
    0.76
    Majority
    0.74
     partially
    0.73
     Majority
    0.72
     multiplier
    0.68
    aku
    0.67
     পার
    0.67
     multiple
    0.65
     kaf
    0.65
     perspective
    0.64
    POSITIVE LOGITS
     total
    2.41
    total
    2.30
    Total
    2.10
     Total
    2.00
     totale
    1.98
    总
    1.90
     totales
    1.90
     总
    1.82
    TOTAL
    1.81
     TOTAL
    1.81
    Act Density 0.159%

    No Known Activations