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

    Neuronpedia

    INDEX
    Explanations

    question prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cashback
    -0.08
     가능합니다
    -0.08
    oupon
    -0.08
     cuivre
    -0.08
    _placeholder
    -0.08
     flotation
    -0.08
     bih
    -0.08
     Menü
    -0.08
     مصنوع
    -0.08
     હાલમાં
    -0.08
    POSITIVE LOGITS
     overcame
    0.12
    였
    0.10
     당시
    0.09
     ছিল
    0.09
     circumstances
    0.09
     involvement
    0.09
     damal
    0.09
    েছিল
    0.09
    だった
    0.09
     उस
    0.09
    Act Density 0.034%

    No Known Activations