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

    Neuronpedia

    INDEX
    Explanations

    setting variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     absolutely
    -0.07
    手续费
    -0.07
    /query
    -0.07
    我们必须
    -0.07
    -server
    -0.06
    中国汽车
    -0.06
    acteria
    -0.06
    del
    -0.06
     Becker
    -0.06
    ================================================================
    -0.06
    POSITIVE LOGITS
    .toObject
    0.07
    ,map
    0.07
     clips
    0.07
    말
    0.07
     같
    0.07
    퉤
    0.07
    kus
    0.07
    .Unlock
    0.07
     реш
    0.07
    .GridView
    0.07
    Act Density 0.082%

    No Known Activations