© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5490
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    call to print() (negative activations)

    python-code · gemini-2.5-flash-lite

    subtracting one from index or count

    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
    V
    -0.03
     V
    -0.03
     [(
    -0.02
     []↵
    -0.02
     _
    -0.02
     []↵↵
    -0.01
     %
    -0.01
    .pop
    -0.01
     G
    -0.01
    %
    -0.01
    POSITIVE LOGITS
    '.
    0.03
    ).
    0.02
    ].
    0.02
    }:
    0.02
    ter
    0.01
    }
    0.01
    ().
    0.01
    }"
    0.01
    ress
    0.01
    },
    0.01
    Activations Density 67.903%

    No Known Activations