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

    Neuronpedia

    INDEX
    Explanations

    Locations and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    су
    -0.08
     someday
    -0.07
    mot
    -0.07
     phóng
    -0.06
     altijd
    -0.06
     challenger
    -0.06
     lugares
    -0.06
     سخن
    -0.06
    ADI
    -0.06
    kům
    -0.06
    POSITIVE LOGITS
        	
↵
    0.06
     newsletter
    0.06
     Interview
    0.06
     hub
    0.06
     agents
    0.06
    ﻠ
    0.06
     Span
    0.06
     Sadly
    0.06
    Driver
    0.06
    arking
    0.06
    Act Density 0.013%

    No Known Activations