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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    positions
    -0.07
    薪水
    -0.07
    resolver
    -0.07
    //----------------------------------------------------------------
    -0.07
    MN
    -0.06
    NC
    -0.06
     Functional
    -0.06
     pequ
    -0.06
    VIRTUAL
    -0.06
    OMP
    -0.06
    POSITIVE LOGITS
    댕
    0.07
    岊
    0.07
     일단
    0.07
     skincare
    0.07
     Barbie
    0.07
     magic
    0.06
    甓
    0.06
    槜
    0.06
     ltd
    0.06
    游泳
    0.06
    Act Density 0.196%

    No Known Activations