© 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. MLP
    9. 6-MLP
    11. 6126
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .s or _s followed by shape

    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
    .path
    -0.04
    join
    -0.04
    ame
    -0.03
    ject
    -0.03
    le
    -0.03
    ithm
    -0.03
     number
    -0.02
    les
    -0.02
     f
    -0.02
    ing
    -0.02
    POSITIVE LOGITS
    loat
    0.07
    ize
    0.06
    tices
    0.06
    ilities
    0.06
     between
    0.05
    iz
    0.05
    times
    0.05
    ized
    0.05
     found
    0.05
    >
    0.04
    Activations Density 10.912%

    No Known Activations