© 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. 6165
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    json.load or json.dump

    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
     dfs
    -0.06
    .e
    -0.05
    gorithm
    -0.04
     algorithm
    -0.04
    jkstra
    -0.04
     =
    -0.04
     bre
    -0.04
     Find
    -0.03
     search
    -0.03
    .c
    -0.03
    POSITIVE LOGITS
    .
    0.08
    sert
    0.07
     count
    0.05
    unt
    0.03
    .index
    0.03
     rows
    0.03
    count
    0.02
    ount
    0.02
    _counts
    0.02
    _nodes
    0.02
    Activations Density 69.937%

    No Known Activations