© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    sorting with arguments (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
    prese
    -0.04
     represent
    -0.03
     contain
    -0.03
    anage
    -0.02
     has
    -0.02
    put
    -0.02
    valu
    -0.02
    area
    -0.02
    our
    -0.01
    team
    -0.01
    Positive Logits
     P
    0.03
    P
    0.03
    p
    0.02
    ath
    0.01
     cont
    0.01
    ast
    0.01
    q
    0.01
    olution
    0.01
    .x
    0.00
    '
    0.00
    Activations Density 87.688%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to `max` variable

    python-code · gemini-2.5-flash-lite

    `None` values (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
    udok
    -0.09
    uristic
    -0.09
    raph
    -0.09
     heuristic
    -0.09
     vertex
    -0.09
    _vertex
    -0.09
    vertex
    -0.08
    ateg
    -0.08
    graph
    -0.08
    (graph
    -0.08
    Positive Logits
    apac
    0.07
     Testing
    0.07
     Test
    0.06
    č
    0.06
    _end
    0.06
    apacity
    0.06
    _start
    0.06
     end
    0.05
     dp
    0.05
    end
    0.05
    Activations Density 100.000%

    No Known Activations