© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3446
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    opening parenthesis followed by value in call (negative activations)

    python-code · gemini-2.5-flash-lite

    function call 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
     temp
    -0.04
     def
    -0.02
    e
    -0.02
    _data
    -0.02
    def
    -0.02
    =
    -0.01
    _input
    -0.01
    ce
    -0.01
     e
    -0.01
     -
    -0.01
    POSITIVE LOGITS
     found
    0.05
     assign
    0.04
     process
    0.04
    assign
    0.03
     sele
    0.03
    self
    0.02
    over
    0.02
    ind
    0.02
     self
    0.02
    _move
    0.02
    Activations Density 100.000%

    No Known Activations