© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. MLP
    5. 6-MLP
    6. 3861
    Prev
    Next
    INDEX
    Compare
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment operator (negative activations)

    python-code · gemini-2.5-flash-lite

    "Hello" and "Home" prefixes

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
    ")↵
    -0.04
    ")↵↵
    -0.04
    }")↵
    -0.04
    ')↵
    -0.04
    ')↵↵
    -0.03
    ilename
    -0.03
    }")↵↵
    -0.03
    _file
    -0.03
    ")<|
    -0.03
    ilen
    -0.03
    Positive Logits
     model
    0.03
    4
    0.02
    straint
    0.02
    straints
    0.01
    500
    0.01
     ob
    0.01
     dp
    0.01
    _string
    0.01
    ^
    0.01
    _str
    0.01
    Activations Density 70.885%

    No Known Activations