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

    Neuronpedia

    INDEX
    Explanations

    marking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMUM
    -0.08
    serve
    -0.08
     комбина
    -0.08
    orithms
    -0.08
    illus
    -0.08
     tient
    -0.07
    ాలని
    -0.07
    נה
    -0.07
    ensus
    -0.07
    .Environment
    -0.07
    POSITIVE LOGITS
    ว่า
    0.09
     rằng
    0.08
    ว่
    0.08
     بأنها
    0.08
     labeling
    0.08
    ভ
    0.08
    “一带一路
    0.08
     Reel
    0.08
    稱
    0.08
     grooming
    0.07
    Act Density 0.059%

    No Known Activations