© 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. 3626
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal or function argument (negative activations)

    python-code · gemini-2.5-flash-lite

    float constructor argument

    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
     given
    -0.10
     found
    -0.09
     spe
    -0.06
    .add
    -0.06
    zero
    -0.06
     heapq
    -0.05
    over
    -0.04
    queue
    -0.04
    :-
    -0.04
    .append
    -0.04
    POSITIVE LOGITS
    mport
    0.07
     and
    0.05
     abs
    0.05
    idth
    0.04
    _len
    0.04
     {↵
    0.04
    _size
    0.04
    len
    0.04
     size
    0.04
    _count
    0.04
    Activations Density 99.288%

    No Known Activations