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

    Neuronpedia

    INDEX
    Explanations

    Understanding, opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roommate
    -0.07
    wer
    -0.07
     يجب
    -0.07
     omin
    -0.07
    -origin
    -0.07
    鉄
    -0.07
    -sponsored
    -0.06
     haz
    -0.06
    (Some
    -0.06
     Sorting
    -0.06
    POSITIVE LOGITS
    contri
    0.06
    restore
    0.06
     glBind
    0.06
     DT
    0.06
    lerdir
    0.06
     url
    0.06
     péri
    0.05
    yp
    0.05
    (FLAGS
    0.05
     bezier
    0.05
    Act Density 0.031%

    No Known Activations