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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _school
    -0.07
    )'
    -0.07
     rowNum
    -0.07
    ࡢ
    -0.06
    ucursal
    -0.06
    <title
    -0.06
    �
    -0.06
     mole
    -0.06
    (nombre
    -0.06
    '>
    -0.06
    POSITIVE LOGITS
    rites
    0.07
    pedia
    0.07
    heit
    0.07
    روف
    0.06
    服务质量
    0.06
    瀱
    0.06
    鲾
    0.06
    远程
    0.06
     protocol
    0.06
    ้ว
    0.06
    Act Density 0.001%

    No Known Activations