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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Russ
    -0.08
     Ern
    -0.08
     ern
    -0.08
     حصول
    -0.08
     situado
    -0.07
     geopolitical
    -0.07
     halen
    -0.07
     eet
    -0.07
     ziyaret
    -0.07
     لوی
    -0.07
    POSITIVE LOGITS
    stu
    0.08
     устройств
    0.08
    334
    0.08
     оставить
    0.07
     शैली
    0.07
    412
    0.07
     dra
    0.07
    nique
    0.07
     स्थापित
    0.07
     найд
    0.07
    Act Density 0.028%

    No Known Activations