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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oste
    -0.07
     bigint
    -0.07
    มาก
    -0.07
    שיר
    -0.07
    Operators
    -0.06
    晔
    -0.06
     năng
    -0.06
    肭
    -0.06
    喆
    -0.06
     std
    -0.06
    POSITIVE LOGITS
    该院
    0.08
    毫无
    0.07
    纠
    0.07
    .Department
    0.07
    一路
    0.07
    سجن
    0.06
     PAT
    0.06
    )')↵
    0.06
     Invent
    0.06
     room
    0.06
    Act Density 0.225%

    No Known Activations