© 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. 3465
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    all with generator expression

    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
    hildren
    -0.04
    ameters
    -0.03
    structions
    -0.03
    endencies
    -0.02
    [(
    -0.02
     has
    -0.02
     is
    -0.02
     can
    -0.02
     Create
    -0.02
    tes
    -0.02
    POSITIVE LOGITS
    endoftext
    0.04
    end
    0.03
    item
    0.02
     end
    0.02
     destination
    0.02
    right
    0.02
    ari
    0.01
     num
    0.01
     target
    0.01
     dest
    0.01
    Activations Density 24.231%

    No Known Activations