© 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. 2-MLP
    11. 8029
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    opening parenthesis `(` (negative activations)

    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
     goal
    -0.16
    oal
    -0.14
     heuristic
    -0.11
    _end
    -0.09
    rontier
    -0.08
    end
    -0.08
    up
    -0.07
     target
    -0.06
    _c
    -0.06
    uristic
    -0.06
    POSITIVE LOGITS
    gram
    0.19
    ual
    0.16
    mory
    0.16
     instruction
    0.14
    ique
    0.14
    il
    0.13
    struction
    0.13
    inal
    0.12
     instructions
    0.12
    ied
    0.12
    Activations Density 99.680%

    No Known Activations