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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    очек
    -0.08
    劳动者
    -0.07
     Instead
    -0.07
     Этот
    -0.07
    뛩
    -0.07
     Card
    -0.07
     loyalty
    -0.06
     Angebot
    -0.06
    atz
    -0.06
     connections
    -0.06
    POSITIVE LOGITS
     unrest
    0.07
    -random
    0.07
    -result
    0.06
    뮨
    0.06
    licer
    0.06
    ден
    0.06
    .Columns
    0.06
    ：%
    0.06
    ⧼
    0.06
     données
    0.06
    Act Density 0.001%

    No Known Activations