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
    细
    -0.07
     Pelosi
    -0.07
    تدى
    -0.06
    .Bl
    -0.06
     filings
    -0.06
     pelic
    -0.06
     FHA
    -0.06
    -SA
    -0.06
     εφαρ
    -0.05
     bites
    -0.05
    POSITIVE LOGITS
    lands
    0.07
    ۲۵
    0.07
     exporters
    0.07
     Вот
    0.06
     Jam
    0.06
     Laur
    0.06
    ースト
    0.06
     Ре
    0.06
     AU
    0.06
     override
    0.06
    Act Density 0.003%

    No Known Activations