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

    Neuronpedia

    INDEX
    Explanations

    lot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мор
    -0.07
    тий
    -0.06
    ?,
    -0.06
     vox
    -0.06
     Muse
    -0.06
     {↵↵↵
    -0.06
     Rewards
    -0.06
    	users
    -0.06
    visit
    -0.06
    .Date
    -0.06
    POSITIVE LOGITS
     Sark
    0.07
    긴
    0.06
     недел
    0.06
    por
    0.06
    تز
    0.06
     destek
    0.06
    失
    0.06
    денти
    0.06
     narciss
    0.06
    Cisco
    0.06
    Act Density 0.025%

    No Known Activations