© 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. 4528
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    part of words ending in 'tion' or 'ment'

    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
    07
    -0.04
    01
    -0.04
    03
    -0.04
    qui
    -0.04
    00
    -0.04
    02
    -0.03
    0
    -0.03
    ]][
    -0.03
    05
    -0.03
    loat
    -0.03
    POSITIVE LOGITS
     %
    0.05
     ]↵
    0.04
    0.04
     <
    0.03
     {
    0.03
     },↵
    0.03
     }↵
    0.03
    zero
    0.02
     O
    0.02
     \
    0.02
    Activations Density 81.129%

    No Known Activations