© 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. 757
    Prev
    Next
    INDEX
    Explanations

    method call `.replace` (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment to variable `f`

    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
    size
    -0.21
    64
    -0.19
    32
    -0.19
    14
    -0.16
    12
    -0.13
    ec
    -0.09
    16
    -0.08
    un
    -0.08
    8
    -0.08
    =
    -0.05
    POSITIVE LOGITS
     ne
    0.14
    80
    0.13
    _ne
    0.12
    ur
    0.09
    _c
    0.09
     next
    0.08
    it
    0.07
    ast
    0.07
     f
    0.05
    ind
    0.03
    Activations Density 100.000%

    No Known Activations