© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 1385
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    after string formatting

    python-code · gemini-2.5-flash-lite

    string literal concatenation with `+` (negative activations)

    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
    Negative Logits
    mport
    -0.05
     function
    -0.04
    dule
    -0.03
    import
    -0.03
     import
    -0.03
    .path
    -0.02
     usage
    -0.02
    (re
    -0.02
    ject
    -0.02
     '__
    -0.02
    POSITIVE LOGITS
     between
    0.06
    tices
    0.05
    times
    0.04
    loat
    0.03
     found
    0.03
     us
    0.03
    lf
    0.02
     typ
    0.02
     based
    0.02
    ays
    0.02
    Activations Density 91.604%

    No Known Activations