© 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. Residual Stream
    9. 7-RESID
    11. 629
    Prev
    Next
    INDEX
    Explanations

    `.` method calls (negative activations)

    python-code · gemini-2.5-flash-lite

    numeric literal 0.5

    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
     p
    -0.21
    is
    -0.18
    app
    -0.16
    airs
    -0.16
    ap
    -0.14
    (op
    -0.14
     min
    -0.13
    ri
    -0.13
    apping
    -0.10
    s
    -0.06
    POSITIVE LOGITS
    on
    0.15
    n
    0.11
     y
    0.11
    om
    0.10
    ield
    0.08
     t
    0.08
     current
    0.05
    ay
    0.02
    '
    0.00
    #
    0.00
    Activations Density 68.372%

    No Known Activations