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

    Neuronpedia

    INDEX
    Explanations

    snippets of computer code, especially with numbers and symbols interspersed

    oai_token-act-pair · gemini-2.0-flash

    code-related terms

    np_token-act-pair-logits · gpt-4o-mini

    1 or 2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.62
     defaultstate
    -0.59
    IBarButtonItem
    -0.57
    возь
    -0.51
    例文帳に追加
    -0.51
     Paglinawan
    -0.51
    ̍t
    -0.50
    GeneratedCode
    -0.50
     Seeder
    -0.48
     Gri
    -0.48
    POSITIVE LOGITS
    ioutil
    0.60
    πή
    0.53
    ️⃣
    0.53
    richTextPanel
    0.52
    ⃣
    0.50
    expandindo
    0.49
    
    0.48
     виправивши
    0.47
    __*/
    0.47
    tagHelperRunner
    0.47
    Act Density 8.411%

    No Known Activations