© 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. 4706
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import defaultdict

    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
    .position
    -0.06
    all
    -0.06
    ].
    -0.04
    _coords
    -0.03
    _position
    -0.03
    ush
    -0.03
     positions
    -0.03
    .con
    -0.03
    _loc
    -0.03
     coordinates
    -0.03
    POSITIVE LOGITS
    ion
    0.05
    <
    0.03
    ateg
    0.03
    ffic
    0.03
    _to
    0.02
    atus
    0.02
    ff
    0.02
    inf
    0.02
    uccess
    0.02
    qrt
    0.02
    Activations Density 56.942%

    No Known Activations