© 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. Residual Stream
    9. 7-RESID
    11. 343
    Prev
    Next
    INDEX
    Explanations

    self.access to attributes and methods

    python-code · gemini-2.5-flash-lite

    re.compile or re.split (negative activations)

    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
    port
    -0.07
    vent
    -0.07
    ist
    -0.05
    ir
    -0.04
    .add
    -0.02
    m
    -0.01
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    _value
    0.26
     Value
    0.26
     value
    0.25
    _values
    0.24
    value
    0.23
     values
    0.22
    values
    0.20
    alue
    0.18
    _val
    0.17
     val
    0.15
    Activations Density 100.000%

    No Known Activations