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

    Neuronpedia

    INDEX
    Explanations

    Demographics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bitmap
    -0.07
    茬
    -0.07
     allo
    -0.07
    วงศ
    -0.07
    Module
    -0.07
    齿
    -0.07
     عبد
    -0.07
    向着
    -0.07
    "))
↵
    -0.06
     commend
    -0.06
    POSITIVE LOGITS
    发达国家
    0.08
     CAST
    0.07
    servers
    0.07
    结果
    0.07
     FilePath
    0.07
     orchestr
    0.07
    单独
    0.07
     investments
    0.07
     incarn
    0.07
    Enemy
    0.07
    Act Density 0.002%

    No Known Activations