© 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. 4866
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    datetime attribute access

    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
    th
    -0.05
    _capacity
    -0.03
     car
    -0.02
    .c
    -0.02
    place
    -0.02
    _c
    -0.02
     cities
    -0.02
     closest
    -0.02
    _length
    -0.02
    .t
    -0.02
    POSITIVE LOGITS
    unter
    0.10
    loc
    0.07
    loat
    0.04
    .in
    0.04
     sys
    0.03
     float
    0.03
    .co
    0.03
    _col
    0.03
     colle
    0.03
    _of
    0.03
    Activations Density 56.157%

    No Known Activations