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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ego
    -0.07
    .scale
    -0.06
    ulant
    -0.06
    원의
    -0.06
    -worker
    -0.06
     lifecycle
    -0.06
    mailbox
    -0.06
    licable
    -0.06
     ایالات
    -0.05
    observ
    -0.05
    POSITIVE LOGITS
    (){
↵
    0.07
    ，↵
    0.07
     vap
    0.06
    rowave
    0.06
     combust
    0.06
     xmlDoc
    0.06
     혼
    0.06
    ода
    0.06
     setuptools
    0.06
     tội
    0.06
    Act Density 0.209%

    No Known Activations