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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Provides
    -0.07
     wreckage
    -0.06
    기도
    -0.06
    orrow
    -0.06
     commanded
    -0.06
     faint
    -0.06
    елов
    -0.06
     Welt
    -0.06
    aturday
    -0.06
    badge
    -0.06
    POSITIVE LOGITS
     Ski
    0.07
    (nx
    0.06
     ON
    0.06
     lyon
    0.06
     Mort
    0.06
     []:↵
    0.06
    .toDouble
    0.06
     музы
    0.06
    .createStatement
    0.06
     Repo
    0.06
    Act Density 0.002%

    No Known Activations