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

    Neuronpedia

    INDEX
    Explanations

    environment variables access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒈥
    0.42
     sigmoid
    0.42
     ricerc
    0.42
     slid
    0.42
    infodisc
    0.42
     bombé
    0.42
     ridges
    0.41
     recalculated
    0.40
    xRt
    0.40
    ByMerging
    0.40
    POSITIVE LOGITS
    环境变量
    0.80
     env
    0.75
    環境
    0.73
     ENV
    0.73
     Env
    0.73
     환경
    0.66
    Env
    0.65
    ENV
    0.65
     environment
    0.62
     NODE
    0.62
    Act Density 0.013%

    No Known Activations