© 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. 5593
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name followed by a number

    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
    66
    -0.06
     between
    -0.04
    mmon
    -0.04
     two
    -0.04
     other
    -0.03
    wo
    -0.03
    other
    -0.02
    42
    -0.02
    44
    -0.02
    (a
    -0.02
    POSITIVE LOGITS
    V
    0.03
     V
    0.03
    :-
    0.01
     G
    0.01
     dictionary
    0.01
    itude
    0.01
    ache
    0.01
    anage
    0.01
    loor
    0.01
    resh
    0.01
    Activations Density 62.043%

    No Known Activations