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

    Neuronpedia

    INDEX
    Explanations

    applying instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    圊
    -0.08
    📔
    -0.08
    .Live
    -0.07
    ":[{↵
    -0.07
     millennium
    -0.07
    ʵ
    -0.07
    ún
    -0.07
    无限
    -0.07
     usar
    -0.07
    .Uint
    -0.07
    POSITIVE LOGITS
    Cond
    0.07
    ko
    0.07
     demonstrates
    0.07
    gan
    0.07
    經常
    0.07
    .dependencies
    0.07
     항상
    0.07
     folds
    0.07
    TextNode
    0.07
     BSON
    0.07
    Act Density 0.022%

    No Known Activations