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

    Neuronpedia

    INDEX
    Explanations

    improving performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tätigkeit
    0.78
     Presence
    0.56
     Distributor
    0.53
    urrection
    0.53
     Destination
    0.52
    adoria
    0.52
    Presence
    0.51
     Celebration
    0.51
     lluvias
    0.51
    濃厚
    0.50
    POSITIVE LOGITS
     performance
    2.36
    performance
    1.99
    性能
    1.98
     Performance
    1.91
    Performance
    1.91
     성능
    1.81
     performances
    1.77
     desempenho
    1.70
     performans
    1.66
     PERFORMANCE
    1.66
    Act Density 1.078%

    No Known Activations