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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )="
    -0.07
     Favorite
    -0.07
    NumberFormatException
    -0.07
     popcorn
    -0.07
    _STATUS
    -0.07
     )}↵↵
    -0.06
    駅徒歩
    -0.06
     });↵↵
    -0.06
    branches
    -0.06
    нут
    -0.06
    POSITIVE LOGITS
     unfolding
    0.06
    Traffic
    0.06
     предполаг
    0.06
    không
    0.06
     matters
    0.06
    ulty
    0.06
    ernational
    0.06
     TG
    0.05
    thetic
    0.05
     librarian
    0.05
    Act Density 0.001%

    No Known Activations