© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1884
    Prev
    Next
    INDEX
    Explanations

    negative numbers in lists or operator strings (negative activations)

    python-code · gemini-2.5-flash-lite

    `os.mkdir` and `os.listdir` calls

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^
    -0.11
     '
    -0.03
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    POSITIVE LOGITS
     -
    0.27
     +
    0.26
     /
    0.20
     *
    0.20
     """
    0.17
     """↵
    0.15
     %
    0.13
    .get
    0.12
     ->
    0.11
     None
    0.09
    Activations Density 99.978%

    No Known Activations