© 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. 2571
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list slicing (negative activations)

    python-code · gemini-2.5-flash-lite

    values in lists/dictionaries

    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
    _op
    -0.04
    arest
    -0.04
    current
    -0.04
    "),↵
    -0.04
     %
    -0.03
    st
    -0.03
     E
    -0.03
    ffe
    -0.03
    [row
    -0.03
     that
    -0.02
    POSITIVE LOGITS
    ":
    0.07
    e
    0.06
    ost
    0.06
     e
    0.05
    ':
    0.05
    ce
    0.05
    ↵↵
    0.05
    ↵
    0.04
     q
    0.04
    ist
    0.04
    Activations Density 99.929%

    No Known Activations