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

    Neuronpedia

    INDEX
    Explanations

    environment variables configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жба
    0.70
    ಬ್ಬ
    0.67
    heal
    0.65
     Gresham
    0.63
    hierarchy
    0.62
     Kant
    0.62
     population
    0.62
     beating
    0.61
    rake
    0.60
    Subview
    0.60
    POSITIVE LOGITS
     environment
    2.21
     Environment
    2.19
    Environment
    2.15
    environment
    2.06
    环境变量
    2.03
     environmental
    2.00
    環境
    1.99
     Environmental
    1.96
     environnement
    1.93
    environnement
    1.93
    Act Density 0.182%

    No Known Activations