© 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. 2-MLP
    11. 4707
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name 'l' used in calculations

    python-code · gemini-2.5-flash-lite

    `for...in` loop or membership check (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
    ateg
    -0.07
     ]↵
    -0.06
    mployee
    -0.05
     }↵
    -0.05
    gist
    -0.05
    mploye
    -0.05
    ory
    -0.05
    hest
    -0.05
    ates
    -0.05
     },↵
    -0.05
    POSITIVE LOGITS
    utation
    0.09
    gth
    0.08
    timal
    0.06
    dint
    0.06
    straints
    0.06
    0.05
    apping
    0.05
    itude
    0.05
    stac
    0.05
     d
    0.05
    Activations Density 100.000%

    No Known Activations