© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6326
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    loop or conditional statement (negative activations)

    python-code · gemini-2.5-flash-lite

    comma following assertion

    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
    join
    -0.03
    oal
    -0.03
    stination
    -0.02
    arget
    -0.02
     goal
    -0.02
     destination
    -0.02
    inal
    -0.02
    ink
    -0.02
     end
    -0.02
    En
    -0.01
    POSITIVE LOGITS
     x
    0.03
    (y
    0.02
    (map
    0.02
     ==
    0.02
     y
    0.02
    =
    0.01
    (w
    0.00
     of
    0.00
     cost
    0.00
     !=
    0.00
    Activations Density 98.951%

    No Known Activations