© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 7609
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list literal `[` or `random.` (negative activations)

    python-code · gemini-2.5-flash-lite

    comparison operator with `==` or `!=`

    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
     dp
    -0.10
    _comb
    -0.06
     calculate
    -0.06
    _counts
    -0.05
     Calculate
    -0.05
     possible
    -0.05
     find
    -0.05
     solve
    -0.04
     comb
    -0.04
    inations
    -0.04
    POSITIVE LOGITS
    _ob
    0.02
     cont
    0.02
    ĩ
    0.02
    ource
    0.02
     rows
    0.02
     items
    0.01
    _from
    0.01
    99
    0.01
    (map
    0.01
     parent
    0.01
    Activations Density 92.112%

    No Known Activations