© 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. 4636
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .format() string method (negative activations)

    python-code · gemini-2.5-flash-lite

    deleting dictionary entries

    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
    '.
    -0.05
     while
    -0.04
    ake
    -0.04
    isit
    -0.04
    80
    -0.03
    ain
    -0.03
    im
    -0.03
    de
    -0.03
    le
    -0.03
    lace
    -0.02
    POSITIVE LOGITS
    rt
    0.13
    ct
    0.07
    lay
    0.05
    ut
    0.04
     function
    0.04
    r
    0.03
     me
    0.03
    k
    0.03
     graph
    0.02
    cur
    0.02
    Activations Density 30.386%

    No Known Activations