© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5512
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    if statement conditional (negative activations)

    python-code · gemini-2.5-flash-lite

    self attribute access

    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
    (r
    -0.05
     q
    -0.04
    q
    -0.04
    .append
    -0.03
     If
    -0.03
    .remove
    -0.03
     -=
    -0.03
    .add
    -0.02
    _r
    -0.02
     +=
    -0.02
    POSITIVE LOGITS
     P
    0.02
    fset
    0.02
     results
    0.02
     possible
    0.01
    hor
    0.01
     directions
    0.01
     break
    0.01
     adjac
    0.01
     moves
    0.01
     dx
    0.01
    Activations Density 99.997%

    No Known Activations