© 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. 5292
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .add method call

    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
    rect
    -0.14
    rior
    -0.11
    ct
    -0.09
    ctor
    -0.07
     Create
    -0.05
    itial
    -0.05
    ec
    -0.04
    ave
    -0.04
    stance
    -0.04
     Initialize
    -0.04
    POSITIVE LOGITS
     pos
    0.09
    and
    0.08
    osition
    0.06
    op
    0.06
    i
    0.06
    os
    0.06
    ies
    0.05
    list
    0.05
    ource
    0.05
    _nodes
    0.04
    Activations Density 12.765%

    No Known Activations