© 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. 5141
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or loop (negative activations)

    python-code · gemini-2.5-flash-lite

    csv writer or dictwriter

    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
    [row
    -0.06
     row
    -0.05
    row
    -0.05
    _row
    -0.05
    (row
    -0.05
     column
    -0.05
    Ï
    -0.05
    ith
    -0.04
     col
    -0.04
    umn
    -0.03
    POSITIVE LOGITS
    (N
    0.02
    qrt
    0.02
    mple
    0.01
    init
    0.01
    (len
    0.01
     map
    0.01
    The
    0.01
     root
    0.01
     x
    0.01
    (map
    0.01
    Activations Density 99.953%

    No Known Activations