© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. MLP
    5. 6-MLP
    6. 5240
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key access (negative activations)

    python-code · gemini-2.5-flash-lite

    opening parenthesis before a string literal

    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
     "
    -0.04
     '
    -0.03
     "__
    -0.03
    .pop
    -0.03
     ",
    -0.03
    erge
    -0.03
     rows
    -0.03
     '__
    -0.03
     ".
    -0.03
    _valid
    -0.03
    POSITIVE LOGITS
    .position
    0.06
     coordinates
    0.05
    .parent
    0.04
    get
    0.04
     Get
    0.04
     get
    0.04
     the
    0.03
    uel
    0.03
    _coords
    0.03
    ame
    0.03
    Activations Density 99.687%

    No Known Activations