© 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
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 3372
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute access before brackets

    python-code · gemini-2.5-flash-lite

    arithmetic operators and slicing (negative activations)

    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
    _to
    -0.04
    a
    -0.04
    ates
    -0.04
    self
    -0.04
    _tasks
    -0.04
    xF
    -0.04
    pected
    -0.03
    _from
    -0.03
     to
    -0.03
     from
    -0.03
    POSITIVE LOGITS
     -
    0.05
    jk
    0.03
    !
    0.03
    0.03
    .st
    0.03
    st
    0.02
     int
    0.02
    St
    0.02
    _states
    0.02
    _step
    0.02
    Activations Density 100.000%

    No Known Activations