© 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. 1470
    Prev
    Next
    INDEX
    Explanations

    `__str__` method formatting or list index (negative activations)

    python-code · gemini-2.5-flash-lite

    itertools imports and functions

    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
    §
    -0.22
    cell
    -0.21
    node
    -0.20
    udent
    -0.19
    _cell
    -0.18
    ity
    -0.18
    erson
    -0.18
    (point
    -0.18
    tem
    -0.17
     cell
    -0.17
    POSITIVE LOGITS
    ½
    0.10
     command
    0.10
     qu
    0.04
    .edges
    0.04
     connections
    0.04
    at
    0.04
    20
    0.02
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 100.000%

    No Known Activations