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

    Neuronpedia

    INDEX
    Explanations

    page

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ama
    -0.08
     pronounce
    -0.08
    หว
    -0.07
     Eg
    -0.07
    Youtube
    -0.07
     cathedral
    -0.07
     тем
    -0.07
     Tavern
    -0.07
     Heard
    -0.07
    .mp
    -0.07
    POSITIVE LOGITS
    Resumen
    0.09
     бумаги
    0.09
    纸
    0.09
     voller
    0.09
     бума
    0.09
     avanti
    0.08
     страницу
    0.08
     बिज
    0.08
     dedicated
    0.08
    Dedicated
    0.08
    Act Density 0.013%

    No Known Activations