© 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. 1015
    Prev
    Next
    INDEX
    Explanations

    numerical values (negative activations)

    python-code · gemini-2.5-flash-lite

    numeric literal in list or dict definition

    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
    58
    -0.21
    45
    -0.15
    59
    -0.14
    100
    -0.09
    10
    -0.08
    path
    -0.07
    6
    -0.06
    ]]↵
    -0.04
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    ^
    0.30
    right
    0.20
    12
    0.15
     us
    0.12
     at
    0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 61.537%

    No Known Activations