© 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. 7547
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random.uniform or random.randint

    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
    ount
    -0.07
    temp
    -0.06
    ual
    -0.04
    tic
    -0.04
     le
    -0.04
    mple
    -0.04
    range
    -0.04
    quired
    -0.04
    ong
    -0.04
    ram
    -0.04
    POSITIVE LOGITS
    atch
    0.06
    ut
    0.06
    A
    0.05
    ats
    0.05
    ati
    0.05
     match
    0.05
    at
    0.05
     P
    0.04
    P
    0.04
    ater
    0.03
    Activations Density 3.493%

    No Known Activations