© 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. 7638
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    parenthesis for function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    self.root attribute

    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
    alse
    -0.04
    rue
    -0.04
    False
    -0.03
    True
    -0.03
     True
    -0.03
     False
    -0.02
    .keys
    -0.02
    =True
    -0.02
    lse
    -0.01
    ()↵
    -0.01
    POSITIVE LOGITS
     while
    0.02
     Get
    0.02
     cur
    0.02
     current
    0.02
     curr
    0.01
    current
    0.01
     _
    0.01
     j
    0.01
     u
    0.01
     i
    0.01
    Activations Density 99.624%

    No Known Activations