© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2829
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    part of variable names or attributes ending in 'd' or 'ed'

    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
    all
    -0.11
    il
    -0.07
    ateg
    -0.06
    ol
    -0.06
    un
    -0.06
    ari
    -0.06
     represe
    -0.06
     representing
    -0.05
     represent
    -0.05
    ef
    -0.05
    POSITIVE LOGITS
     us
    0.06
     between
    0.06
    yp
    0.06
     by
    0.06
     based
    0.06
     on
    0.05
     that
    0.05
     it
    0.05
    _from
    0.05
    _by
    0.05
    Activations Density 46.691%

    No Known Activations