© 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. 4738
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    "hello world" string literals

    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
    isited
    -0.05
    ward
    -0.04
    rack
    -0.04
    o
    -0.04
    l
    -0.04
    ackage
    -0.04
    ck
    -0.03
    ack
    -0.03
    }:
    -0.03
    ron
    -0.03
    POSITIVE LOGITS
     are
    0.05
     is
    0.05
    's
    0.05
     can
    0.04
    """↵
    0.04
    ""
    0.04
     has
    0.03
    tions
    0.03
    ateg
    0.03
     """
    0.03
    Activations Density 15.901%

    No Known Activations