© 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. 4688
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    number followed by (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
    ]]
    -0.09
    )<|
    -0.09
    umn
    -0.08
    )↵
    -0.08
    ):↵
    -0.07
    lambda
    -0.07
    (str
    -0.07
    )↵↵
    -0.06
    (int
    -0.06
     depth
    -0.06
    POSITIVE LOGITS
    _number
    0.12
    _code
    0.12
    _type
    0.12
    _id
    0.12
    _name
    0.11
    _idx
    0.10
     obstac
    0.10
    _coords
    0.10
    _num
    0.10
    _coordinates
    0.10
    Activations Density 59.716%

    No Known Activations