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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Builder
    -0.07
    reads
    -0.07
    سد
    -0.07
     upgrade
    -0.06
    Kit
    -0.06
    	cuda
    -0.06
     ride
    -0.06
    "github
    -0.06
     qualifications
    -0.06
    Plug
    -0.06
    POSITIVE LOGITS
    एम
    0.07
    rub
    0.06
     моб
    0.06
    illisecond
    0.06
    지막
    0.06
    /e
    0.06
    すぎ
    0.06
     Avatar
    0.06
     stran
    0.06
    inosaur
    0.06
    Act Density 0.032%

    No Known Activations