© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    method name `send` (negative activations)

    python-code · gemini-2.5-flash-lite

    .get or .exit

    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
    air
    -0.11
    _comp
    -0.10
    _row
    -0.09
    mp
    -0.09
     comp
    -0.05
    mm
    -0.05
     in
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    POSITIVE LOGITS
    ype
    0.26
     value
    0.21
    location
    0.18
    ilename
    0.18
    direction
    0.18
    ordinates
    0.16
    atus
    0.15
    ategory
    0.15
    label
    0.14
    osition
    0.14
    Activations Density 99.853%

    No Known Activations