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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    烦
    -0.08
    着眼
    -0.07
    一堆
    -0.07
     chuck
    -0.07
     cụ
    -0.07
    .Mapping
    -0.07
    _lens
    -0.07
     wilderness
    -0.07
    ุ
    -0.06
    شو
    -0.06
    POSITIVE LOGITS
    uggested
    0.07
     vẻ
    0.07
    得意
    0.07
    帨
    0.07
     tightly
    0.07
    三点
    0.06
    Four
    0.06
     ücret
    0.06
     annon
    0.06
    😣
    0.06
    Act Density 0.001%

    No Known Activations