© 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. MLP
    9. 6-MLP
    11. 3750
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return followed by len or list (negative activations)

    python-code · gemini-2.5-flash-lite

    parenthesis or start of if statement

    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
     ver
    -0.04
    a
    -0.03
    one
    -0.03
    .set
    -0.03
    ail
    -0.03
     path
    -0.03
    A
    -0.03
    ject
    -0.03
    ackage
    -0.03
    _path
    -0.02
    POSITIVE LOGITS
     dfs
    0.11
    gorithm
    0.08
     algorithm
    0.08
    .values
    0.08
    jkstra
    0.07
     bre
    0.06
    alc
    0.06
     Find
    0.06
     search
    0.06
    _search
    0.06
    Activations Density 96.093%

    No Known Activations