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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remodel
    -0.06
    ме
    -0.06
    금
    -0.06
     경기
    -0.06
    urrencies
    -0.06
    NV
    -0.06
     시즌
    -0.06
     Jasmine
    -0.06
     Supplies
    -0.06
    之后
    -0.06
    POSITIVE LOGITS
     inefficient
    0.07
    klady
    0.07
    點
    0.07
     spreading
    0.06
    :@{
    0.06
    (world
    0.06
    Agency
    0.06
    _gb
    0.06
    _uv
    0.06
     обла
    0.06
    Act Density 0.001%

    No Known Activations