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

    Neuronpedia

    INDEX
    Explanations

    Dockerfile instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ingredient
    0.43
     alcool
    0.40
     primitiva
    0.40
     Ingredient
    0.39
    Ingredient
    0.38
     afficher
    0.38
    Parsing
    0.38
    鳖
    0.38
    numOf
    0.37
     coag
    0.37
    POSITIVE LOGITS
    env
    0.55
    ENV
    0.51
    RUN
    0.50
     ENV
    0.46
     env
    0.44
     Env
    0.42
    复制
    0.40
    COPY
    0.39
    environ
    0.39
    CMD
    0.38
    Act Density 0.006%

    No Known Activations