© 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. 1130
    Prev
    Next
    INDEX
    Explanations

    assignment statement (negative activations)

    python-code · gemini-2.5-flash-lite

    self.imagpart or self.name

    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
    ģ
    -0.24
    _and
    -0.21
     si
    -0.21
     two
    -0.19
     hi
    -0.17
    ati
    -0.16
    te
    -0.15
    40
    -0.13
    ls
    -0.13
    ti
    -0.13
    POSITIVE LOGITS
     sim
    0.16
     log
    0.14
    _r
    0.13
    _node
    0.12
    ĸ
    0.12
    im
    0.12
    _l
    0.09
    r
    0.04
    11
    0.04
    '
    0.00
    Activations Density 100.000%

    No Known Activations