© 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. 2-MLP
    11. 4958
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key access

    python-code · gemini-2.5-flash-lite

    loop variable assignment (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
    (op
    -0.10
     operation
    -0.08
    ot
    -0.06
    ob
    -0.06
    _ob
    -0.05
     obstac
    -0.04
     op
    -0.04
     are
    -0.04
     open
    -0.04
    ran
    -0.04
    POSITIVE LOGITS
    02
    0.09
    001
    0.08
    03
    0.07
    05
    0.06
    over
    0.06
    08
    0.06
    110
    0.06
     visited
    0.06
    term
    0.06
    zero
    0.05
    Activations Density 100.000%

    No Known Activations