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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sexy
    -0.08
    下面
    -0.07
     Facility
    -0.07
     Villa
    -0.07
    _after
    -0.07
    .ca
    -0.07
    דף
    -0.07
     Landscape
    -0.07
     PHOTO
    -0.07
    /system
    -0.07
    POSITIVE LOGITS
    ession
    0.07
    nnen
    0.07
    条评论
    0.07
     expectedResult
    0.07
     Dere
    0.07
    鹍
    0.07
    �
    0.07
    籁
    0.07
     SearchResult
    0.07
    рут
    0.07
    Act Density 0.002%

    No Known Activations