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

    Neuronpedia

    INDEX
    Explanations

    install packages and development tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bootcamp
    0.89
     แล
    0.81
     voucher
    0.79
     kỷ
    0.75
    SpringBoot
    0.75
     disconnection
    0.74
     Sain
    0.73
     accountability
    0.72
     démarrage
    0.71
     Displacement
    0.71
    POSITIVE LOGITS
     lib
    1.05
    lib
    1.04
     packages
    0.98
    安装
    0.98
    package
    0.94
    Package
    0.94
    包
    0.93
     package
    0.93
    Install
    0.93
    Packages
    0.93
    Act Density 0.290%

    No Known Activations