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

    Neuronpedia

    INDEX
    Explanations

    technical file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elever
    0.24
     Bisby
    0.23
     sickly
    0.22
     peau
    0.21
    诏
    0.21
     wodurch
    0.21
     vết
    0.20
    腌
    0.20
     vraie
    0.20
    龋
    0.20
    POSITIVE LOGITS
    security
    0.27
    utils
    0.27
    config
    0.26
    scripts
    0.25
    package
    0.25
    Config
    0.25
    notifications
    0.24
    scheduling
    0.24
    api
    0.24
    register
    0.24
    Act Density 0.286%

    No Known Activations