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

    Neuronpedia

    Jacobian LensNEW
    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. 661
    Prev
    Next
    INDEX
    Explanations

    url or except or math (negative activations)

    python-code · gemini-2.5-flash-lite

    except blocks

    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
    ject
    -0.15
    li
    -0.12
    par
    -0.12
    time
    -0.11
    op
    -0.10
    array
    -0.10
    test
    -0.10
    input
    -0.08
     True
    -0.06
    (ro
    -0.05
    POSITIVE LOGITS
    all
    0.38
     """
    0.23
     """↵
    0.21
    unction
    0.15
     an
    0.11
     generate
    0.10
     {↵
    0.05
     ["
    0.04
    '
    0.00
    #
    0.00
    Activations Density 73.651%

    No Known Activations