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

    Neuronpedia

    INDEX
    Explanations

    Abstract concepts/ideas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    路由器
    -0.08
    Micro
    -0.07
    бли
    -0.07
    classnames
    -0.07
    -readable
    -0.07
    人次
    -0.06
     pami
    -0.06
    orthy
    -0.06
     relief
    -0.06
     ):↵↵
    -0.06
    POSITIVE LOGITS
    ƙ
    0.08
    amic
    0.07
    做事
    0.07
    廊坊
    0.07
    ➮
    0.07
    attro
    0.07
    _FACT
    0.07
    Türkiye
    0.07
    _gold
    0.07
     zoekt
    0.07
    Act Density 0.137%

    No Known Activations