© 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. 4722
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal in print/input

    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
     "
    -0.06
    type
    -0.05
    ).
    -0.05
    rue
    -0.04
    -0.04
    or
    -0.04
     '
    -0.03
    adjac
    -0.03
     +
    -0.03
    j
    -0.03
    POSITIVE LOGITS
    ray
    0.08
    arent
    0.05
     representing
    0.04
     read
    0.04
     In
    0.04
     in
    0.04
    un
    0.03
     parent
    0.03
    um
    0.03
    ]][
    0.03
    Activations Density 3.535%

    No Known Activations