© 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. 2679
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .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
    join
    -0.05
    lable
    -0.03
     new
    -0.03
    nt
    -0.03
     are
    -0.03
     can
    -0.02
     found
    -0.02
     the
    -0.02
    st
    -0.02
    ?
    -0.02
    POSITIVE LOGITS
    ="
    0.09
    ='
    0.09
    is
    0.07
    =
    0.07
    vel
    0.06
    heck
    0.05
    =True
    0.05
     count
    0.05
    .is
    0.05
     check
    0.05
    Activations Density 43.599%

    No Known Activations