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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     populous
    -0.09
    芽
    -0.08
    世
    -0.08
     anl
    -0.08
     amassed
    -0.08
     eccles
    -0.07
     lens
    -0.07
     laatst
    -0.07
     Atu
    -0.07
    -0.07
    POSITIVE LOGITS
     généralement
    0.09
    Generally
    0.08
     yleensä
    0.08
     affaire
    0.08
     pissed
    0.08
     Allgemeinen
    0.08
     ખાત
    0.08
    ٹنگ
    0.07
     структура
    0.07
     priporoč
    0.07
    Act Density 0.014%
    No Known Activations