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

    Neuronpedia

    INDEX
    Explanations

    w

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     campañas
    -0.08
    ecil
    -0.08
    urb
    -0.08
    obile
    -0.08
     Cashback
    -0.08
     telefonu
    -0.08
     egiten
    -0.08
    ล็
    -0.08
    /card
    -0.07
    ethoden
    -0.07
    POSITIVE LOGITS
     попасть
    0.09
     выйти
    0.08
     выхода
    0.08
     replacement
    0.08
    僕
    0.08
     мин
    0.07
     exit
    0.07
     заменить
    0.07
    ornar
    0.07
     closing
    0.07
    Act Density 0.001%

    No Known Activations