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

    Neuronpedia

    INDEX
    Explanations

    Health/well-being benefits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ترة
    -0.07
    ровод
    -0.07
    andas
    -0.07
     changed
    -0.06
    結
    -0.06
    率
    -0.06
    易
    -0.06
     Зем
    -0.06
     Mandatory
    -0.06
     △
    -0.06
    POSITIVE LOGITS
     collabor
    0.07
    ″E
    0.07
     unus
    0.07
     cosm
    0.07
     unm
    0.06
    .admin
    0.06
     تحصیل
    0.06
     Cumhuriyet
    0.06
    .Sm
    0.06
    apur
    0.06
    Act Density 0.054%

    No Known Activations