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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pan
    -0.07
     ViewChild
    -0.07
    新闻
    -0.06
    YOU
    -0.06
     Hue
    -0.06
    .(*
    -0.06
     ▼
    -0.06
    Win
    -0.06
    BF
    -0.06
    PB
    -0.06
    POSITIVE LOGITS
    (nums
    0.07
    顾
    0.07
    就是
    0.07
    _aug
    0.06
    -components
    0.06
    agra
    0.06
     conducts
    0.06
    ैट
    0.06
    )*/↵
    0.06
     دفاع
    0.06
    Act Density 0.019%

    No Known Activations