© 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. 4384
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .pop() method (negative activations)

    python-code · gemini-2.5-flash-lite

    .clear() or os.environ or .engine=

    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
    ef
    -0.03
    sw
    -0.02
    dates
    -0.01
    ask
    -0.01
    item
    -0.01
    asks
    -0.01
    ra
    -0.01
     item
    -0.01
    per
    -0.00
    ound
    -0.00
    POSITIVE LOGITS
    _an
    0.06
     an
    0.05
    an
    0.05
    ant
    0.04
    ance
    0.03
     can
    0.02
    ar
    0.02
     Par
    0.01
    lan
    0.01
    18
    0.01
    Activations Density 97.115%

    No Known Activations