© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. MLP
    5. 6-MLP
    6. 3821
    Prev
    Next
    INDEX
    Compare
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignments or method calls (negative activations)

    python-code · gemini-2.5-flash-lite

    start of a code block

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
    jkstra
    -0.05
    ~
    -0.04
                ↵
    -0.04
    unter
    -0.04
            ↵
    -0.04
     representing
    -0.04
                    ↵
    -0.03
    ool
    -0.03
     ob
    -0.03
    %
    -0.03
    Positive Logits
    },↵
    0.04
    ty
    0.04
     True
    0.03
    th
    0.02
     False
    0.02
    arg
    0.02
    ['
    0.01
    _end
    0.01
    end
    0.01
     end
    0.01
    Activations Density 45.449%

    No Known Activations