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

    Neuronpedia

    INDEX
    Explanations

    programming package

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.61
     छापा
    0.53
     maggio
    0.50
    DEBUGFS
    0.48
     geográfica
    0.48
     préférable
    0.47
     градусов
    0.47
     जाता
    0.47
     पाठ्यक्रम
    0.46
     mecánica
    0.46
    POSITIVE LOGITS
     package
    1.00
    包
    1.00
     pack
    0.98
     paquete
    0.96
     Pack
    0.94
     paket
    0.93
     Package
    0.93
     packages
    0.90
     PACK
    0.88
    package
    0.87
    Act Density 0.022%

    No Known Activations