© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4499
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list elements separated by comma (negative activations)

    python-code · gemini-2.5-flash-lite

    self.model assignment

    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
    ffic
    -0.04
    vers
    -0.04
    jective
    -0.04
    gest
    -0.04
    rid
    -0.04
    lock
    -0.04
    que
    -0.04
    cep
    -0.04
    ip
    -0.04
    rap
    -0.04
    POSITIVE LOGITS
    m
    0.03
    mit
    0.02
    0
    0.01
    n
    0.01
    c
    0.01
    t
    0.01
    <extra_output_id:2047>
    0.01
    ge
    0.00
    '
    0.00
    #
    0.00
    Activations Density 99.517%

    No Known Activations