© 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. 7199
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or len() call (negative activations)

    python-code · gemini-2.5-flash-lite

    method calls and definitions

    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
    re
    -0.03
    .remove
    -0.03
    es
    -0.02
    .add
    -0.01
    _id
    -0.01
     values
    -0.01
     code
    -0.01
     set
    -0.01
     can
    -0.01
     has
    -0.01
    POSITIVE LOGITS
    =True
    0.06
    xF
    0.05
    .p
    0.03
    loat
    0.03
    _and
    0.02
    self
    0.02
    .random
    0.02
    _neighbor
    0.02
    ward
    0.02
     state
    0.02
    Activations Density 83.361%

    No Known Activations