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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .loaded
    -0.09
    -loaded
    -0.09
     UIBar
    -0.08
     показатель
    -0.08
     Loaded
    -0.07
     businessmen
    -0.07
    ];
↵
    -0.07
     prudent
    -0.07
     (!
    -0.07
     UN
    -0.07
    POSITIVE LOGITS
    مالك
    0.08
    (datas
    0.08
    Neben
    0.08
     reels
    0.08
    素材
    0.08
     loose
    0.08
    (regex
    0.07
     volunteers
    0.07
     آزادی
    0.07
     مقابل
    0.07
    Act Density 0.156%

    No Known Activations