© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1579
    Prev
    Next
    INDEX
    Explanations

    string literal assignment (negative activations)

    python-code · gemini-2.5-flash-lite

    numeric literal for 10

    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
    [str
    -0.30
    (str
    -0.26
     str
    -0.24
    str
    -0.19
    _str
    -0.18
    _string
    -0.18
    _len
    -0.13
    150
    -0.10
    14
    -0.09
    13
    -0.09
    POSITIVE LOGITS
    09
    0.10
    0.07
    0.06
    38
    0.05
    6
    0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 100.000%

    No Known Activations