Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     السيطرة
    -0.09
    Transferred
    -0.09
     Antibi
    -0.09
     antibiotic
    -0.08
     چیف
    -0.08
     poured
    -0.08
    лишком
    -0.08
    .calls
    -0.08
     القوات
    -0.08
     dispatched
    -0.08
    POSITIVE LOGITS
    Markdown
    0.13
     Markdown
    0.12
    emoji
    0.10
     markdown
    0.10
    textarea
    0.10
    Emoji
    0.10
     emoji
    0.09
     Mermaid
    0.09
    renderer
    0.09
     tooling
    0.09
    Act Density 0.003%

    No Known Activations