© 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. 4669
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    calling a function or method (negative activations)

    python-code · gemini-2.5-flash-lite

    re.search and hashlib

    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
    _for
    -0.06
    _position
    -0.06
    .position
    -0.06
    att
    -0.05
    _with
    -0.05
    _and
    -0.05
    ith
    -0.04
    _of
    -0.04
    _coords
    -0.03
     positions
    -0.03
    POSITIVE LOGITS
    ce
    0.04
    e
    0.04
    ud
    0.03
     e
    0.03
    ist
    0.03
    or
    0.02
    _tra
    0.02
    n
    0.02
    [i
    0.02
    ner
    0.02
    Activations Density 99.993%

    No Known Activations