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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    াষ
    -0.09
     davantage
    -0.08
     Gentle
    -0.08
     promedio
    -0.08
     truc
    -0.08
     развод
    -0.08
     Holm
    -0.07
     sext
    -0.07
     получится
    -0.07
     flattering
    -0.07
    POSITIVE LOGITS
    -da
    0.08
     proceeding
    0.08
    Comm
    0.08
     подготов
    0.07
     дороги
    0.07
    Pts
    0.07
    .↵↵↵↵
    0.07
    لاسه
    0.07
    .org
    0.07
    ின்ற
    0.07
    Act Density 0.003%

    No Known Activations