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

    Neuronpedia

    INDEX
    Explanations

    mixture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rok
    -0.07
     friendship
    -0.07
     youth
    -0.06
    StrLn
    -0.06
     siyaset
    -0.06
     Eli
    -0.06
    -policy
    -0.06
     athletes
    -0.06
    ("..
    -0.06
     Anat
    -0.06
    POSITIVE LOGITS
    ULATOR
    0.06
     актив
    0.06
    важа
    0.06
    .chapter
    0.06
     تنظيف
    0.06
     podpor
    0.06
     ActionBar
    0.06
    ومتر
    0.06
     ')
↵
    0.06
    ..."↵↵
    0.06
    Act Density 0.009%

    No Known Activations