© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    character manipulation with 97 (negative activations)

    python-code · gemini-2.5-flash-lite

    `chr` function argument

    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
    isited
    -0.23
    ta
    -0.22
     visited
    -0.21
    visited
    -0.20
    Ľ
    -0.18
    xa
    -0.16
    64
    -0.15
    65
    -0.14
    Ĩ
    -0.14
    _v
    -0.13
    POSITIVE LOGITS
    and
    0.15
    28
    0.09
    29
    0.08
    _num
    0.07
    der
    0.07
    or
    0.06
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 99.776%

    No Known Activations