© 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. 410
    Prev
    Next
    INDEX
    Explanations

    not in operator

    python-code · gemini-2.5-flash-lite

    re.search and set() (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
     at
    -0.06
    .read
    -0.06
     ve
    -0.04
    _input
    -0.03
    path
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    ]]
    0.36
    ]:↵
    0.29
    ))<|
    0.25
    ]],
    0.24
     import
    0.23
     +=
    0.21
     -=
    0.18
    ")<|
    0.10
    ))
    0.10
    splay
    0.07
    Activations Density 99.995%

    No Known Activations