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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .number
    -0.08
     Rd
    -0.07
    -information
    -0.07
     Cherry
    -0.07
     setValue
    -0.07
    Mas
    -0.07
     Chr
    -0.06
     Nec
    -0.06
    .Exception
    -0.06
    ducers
    -0.06
    POSITIVE LOGITS
    텀
    0.08
    ımı
    0.07
    生活水平
    0.07
    幽默
    0.07
    バッグ
    0.07
     пенси
    0.07
    dık
    0.07
     Swim
    0.07
     london
    0.07
    꿋
    0.06
    Act Density 0.003%

    No Known Activations