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

    Neuronpedia

    INDEX
    Explanations

    explicit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (domain
    -0.08
    ystems
    -0.08
     concur
    -0.08
    contexts
    -0.08
     herd
    -0.08
    Domains
    -0.07
    singleton
    -0.07
    전체
    -0.07
     warmed
    -0.07
    (enemy
    -0.07
    POSITIVE LOGITS
     تفاصيل
    0.10
     detailing
    0.09
     details
    0.09
     detail
    0.08
     detalles
    0.08
     વિગતો
    0.08
     détails
    0.08
    மான
    0.08
     جدًا
    0.08
     genoeg
    0.08
    Act Density 0.007%

    No Known Activations