© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    string literals 'str' (negative activations)

    python-code · gemini-2.5-flash-lite

    chr function calls

    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
    _co
    -0.18
     ↵
    -0.15
    .t
    -0.14
    _in
    -0.12
    .re
    -0.11
     w
    -0.10
     al
    -0.05
    '
    0.00
    #
    0.00
    &
    0.00
    POSITIVE LOGITS
    .ran
    0.45
    .randint
    0.38
    _shortest
    0.32
    .random
    0.31
    .edges
    0.27
     Output
    0.26
    tem
    0.19
    arch
    0.18
    .num
    0.17
    _conne
    0.15
    Activations Density 98.524%

    No Known Activations