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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    こちら
    -0.06
    ottie
    -0.06
     کردم
    -0.06
    �
    -0.06
     már
    -0.06
    }<
    -0.06
     设置
    -0.06
     "");
↵
    -0.06
     انسانی
    -0.06
    ");
↵
    -0.06
    POSITIVE LOGITS
    alysis
    0.07
     leases
    0.07
    Seed
    0.06
    .Admin
    0.06
     HDD
    0.06
    _deck
    0.06
    /english
    0.06
    classes
    0.06
    irc
    0.06
    ress
    0.06
    Act Density 0.119%

    No Known Activations