© 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
    No Explanations Found
    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
    /
    -0.33
     /
    -0.21
     //
    -0.18
    ati
    -0.12
    timal
    -0.11
    dint
    -0.11
    straints
    -0.10
    prese
    -0.10
    stac
    -0.09
    didate
    -0.09
    Positive Logits
    False
    0.07
     \
    0.06
    02
    0.05
    001
    0.05
    03
    0.05
    08
    0.04
    110
    0.04
    05
    0.03
    123
    0.03
    000
    0.03
    Activations Density 79.659%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call after .randint (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
     un
    -0.11
    ÷
    -0.10
    Á
    -0.10
    ø
    -0.10
    þ
    -0.10
    À
    -0.10
    û
    -0.10
    õ
    -0.10
    ý
    -0.10
    ú
    -0.10
    Positive Logits
    out
    0.13
    tic
    0.12
    param
    0.07
    args
    0.06
    own
    0.05
    ue
    0.05
    all
    0.05
    ariable
    0.04
    arg
    0.04
    par
    0.03
    Activations Density 99.996%

    No Known Activations