© 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. 7409
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    recv method or records attribute

    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
    ces
    -0.10
    ce
    -0.09
    cies
    -0.08
    anage
    -0.07
    ger
    -0.07
    ating
    -0.06
    cy
    -0.06
    ated
    -0.06
    ats
    -0.06
    are
    -0.06
    POSITIVE LOGITS
    I
    0.06
    ram
    0.06
    ords
    0.05
    isit
    0.05
    ord
    0.04
    ¿
    0.04
    ul
    0.04
    ression
    0.04
     second
    0.03
    or
    0.03
    Activations Density 20.086%

    No Known Activations