© 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. 5174
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    json.dumps arguments

    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
    ood
    -0.06
    uzz
    -0.05
    ed
    -0.05
    ters
    -0.05
    ter
    -0.04
    ?
    -0.04
    K
    -0.04
    od
    -0.04
    onent
    -0.04
    xb
    -0.04
    POSITIVE LOGITS
    fs
    0.07
    ¤
    0.06
    Ĥ
    0.06
    f
    0.05
    xf
    0.05
    fi
    0.05
    ft
    0.05
     final
    0.05
    fe
    0.05
    F
    0.04
    Activations Density 57.753%

    No Known Activations