© 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. 4871
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `__init__` method and `print` calls (negative activations)

    python-code · gemini-2.5-flash-lite

    attributes in class definitions

    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
    instance
    -0.04
     given
    -0.03
     dist
    -0.03
     distances
    -0.03
     distance
    -0.02
     cost
    -0.02
    lines
    -0.01
    [j
    -0.01
     [(
    -0.01
     Initialize
    -0.01
    POSITIVE LOGITS
     break
    0.04
    <extra_output_id:2047>
    0.02
    is
    0.02
    ",↵
    0.01
     L
    0.01
     else
    0.01
    }
    0.01
     the
    0.01
     j
    0.01
    .start
    0.01
    Activations Density 99.990%

    No Known Activations