© 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. Residual Stream
    5. 7-RESID
    6. 1684
    Prev
    Next
    INDEX
    Explanations

    tkinter module, attributes, or method calls (negative activations)

    python-code · gemini-2.5-flash-lite

    argument for 'anchor'

    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
    cond
    -0.31
     representing
    -0.26
     This
    -0.22
    ().
    -0.17
    _solution
    -0.17
     dest
    -0.16
     t
    -0.15
    :
    -0.13
    ct
    -0.11
     first
    -0.11
    POSITIVE LOGITS
     block
    0.14
    or
    0.13
    -
    0.11
    ):
    0.10
     {
    0.10
     target
    0.10
    b
    0.08
    '
    0.08
    25
    0.08
    0
    0.07
    Activations Density 99.993%

    No Known Activations