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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fighter
    -0.07
     Cumhuriyeti
    -0.06
    south
    -0.06
     univers
    -0.06
     bordered
    -0.06
     refining
    -0.06
     якої
    -0.06
    QUOTE
    -0.06
     lakh
    -0.06
    Ack
    -0.06
    POSITIVE LOGITS
    lesc
    0.06
     لذا
    0.06
    →→
    0.06
     첨부파일
    0.06
    кування
    0.06
     lite
    0.06
     slack
    0.06
     FOOD
    0.06
    util
    0.06
    iễn
    0.06
    Act Density 0.001%

    No Known Activations