© 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. 907
    Prev
    Next
    INDEX
    Explanations

    np.dot function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    send or read methods

    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
    de
    -0.24
    les
    -0.20
    ount
    -0.19
    ci
    -0.12
     l
    -0.12
    stru
    -0.11
    or
    -0.11
    ore
    -0.10
    alculate
    -0.09
    ed
    -0.09
    POSITIVE LOGITS
    if
    0.19
     di
    0.13
    ase
    0.08
    as
    0.08
    ep
    0.05
    h
    0.05
    n
    0.05
    t
    0.05
    '
    0.00
    #
    0.00
    Activations Density 99.997%

    No Known Activations