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

    Neuronpedia

    INDEX
    Explanations

    cost savings, no sacrificing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     photographie
    -0.08
     телефону
    -0.08
    telefono
    -0.08
     шт
    -0.08
     Misc
    -0.08
     телефона
    -0.08
     naturale
    -0.08
     CEP
    -0.08
     Dise
    -0.08
    prus
    -0.08
    POSITIVE LOGITS
     integrity
    0.09
    .gz
    0.09
     still
    0.09
    不过
    0.09
     trotzdem
    0.09
    可靠
    0.08
     dennoch
    0.08
    完整
    0.08
     performant
    0.08
    仍
    0.08
    Act Density 0.039%

    No Known Activations