© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3606
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random.choice method

    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
    city
    -0.05
    ject
    -0.03
    ves
    -0.03
    li
    -0.03
    par
    -0.02
    ed
    -0.02
    time
    -0.02
    op
    -0.02
    m
    -0.02
    array
    -0.02
    POSITIVE LOGITS
    all
    0.08
    out
    0.07
    o
    0.06
    own
    0.05
    qrt
    0.05
     o
    0.05
    t
    0.05
    oc
    0.05
    in
    0.05
     """
    0.05
    Activations Density 19.049%

    No Known Activations