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

    Neuronpedia

    INDEX
    Explanations

    который

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     спас
    -0.07
     Queries
    -0.07
     rock
    -0.07
     Stuff
    -0.06
     vacc
    -0.06
    object
    -0.06
     sw
    -0.06
     не
    -0.06
     north
    -0.06
    copy
    -0.06
    POSITIVE LOGITS
    _SEL
    0.07
    irst
    0.06
    autorelease
    0.06
     которые
    0.06
     geschichten
    0.06
    .Local
    0.06
     Fransa
    0.06
    IRST
    0.06
    ovan
    0.06
    ]){
↵
    0.06
    Act Density 0.037%

    No Known Activations