© 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. 7018
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    not in

    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
    join
    -0.06
    stination
    -0.05
    form
    -0.05
    oal
    -0.04
    urrent
    -0.04
    arget
    -0.04
    [current
    -0.03
    (current
    -0.03
    est
    -0.03
    cur
    -0.03
    POSITIVE LOGITS
    isited
    0.09
    ith
    0.06
    orted
    0.05
     with
    0.05
    maining
    0.05
    visited
    0.04
    quired
    0.04
    use
    0.04
     found
    0.04
    ted
    0.04
    Activations Density 67.274%

    No Known Activations