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

    Neuronpedia

    INDEX
    Explanations

    environment variables and configuration secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lucene
    0.44
     surgeons
    0.43
     chirurg
    0.43
     dilat
    0.42
     compressive
    0.41
     stenosis
    0.41
    frameCount
    0.41
     sculpting
    0.41
    UnaryOperation
    0.40
     sculptural
    0.40
    POSITIVE LOGITS
     Config
    1.22
     config
    1.19
    Config
    1.19
     configuration
    1.12
     Configuration
    1.12
    Configuration
    1.09
    配置文件
    1.09
     конфигура
    1.05
    config
    1.04
    configuration
    0.96
    Act Density 0.033%

    No Known Activations