© 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. 451
    Prev
    Next
    INDEX
    Explanations

    side of tk.LEFT

    python-code · gemini-2.5-flash-lite

    index in a list assignment (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
    mo
    -0.42
    la
    -0.18
    lat
    -0.11
    id
    -0.10
    ac
    -0.05
    n
    -0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    T
    0.24
    16
    0.13
     t
    0.09
    ree
    0.08
    tion
    0.07
    _t
    0.06
    8
    0.05
    A
    0.04
    E
    0.04
    '
    0.00
    Activations Density 100.000%

    No Known Activations