© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4196
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    constructor parameter 'self' (negative activations)

    python-code · gemini-2.5-flash-lite

    instance variable assignment

    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
    .position
    -0.05
    _coords
    -0.03
    _position
    -0.03
     positions
    -0.03
    vai
    -0.03
    ron
    -0.03
     heap
    -0.03
     -=
    -0.03
    _loc
    -0.03
     tuple
    -0.03
    POSITIVE LOGITS
     all
    0.03
     path
    0.03
    all
    0.03
    _path
    0.03
    path
    0.03
     route
    0.02
     paths
    0.02
    _tra
    0.02
     any
    0.02
    _paths
    0.02
    Activations Density 99.997%

    No Known Activations