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

    Neuronpedia

    INDEX
    Explanations

    rat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idue
    -0.07
    DUCTION
    -0.07
     discs
    -0.07
     professions
    -0.07
    文件
    -0.07
    로
    -0.07
    _relationship
    -0.07
     newspaper
    -0.07
    ウェ
    -0.06
     gauge
    -0.06
    POSITIVE LOGITS
    evším
    0.07
     odom
    0.07
    ,len
    0.06
    .localScale
    0.06
    iropr
    0.06
     spilled
    0.06
     슬
    0.06
     Yorkers
    0.06
     embraces
    0.06
    DataSet
    0.06
    Act Density 0.019%

    No Known Activations