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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Libr
    -0.09
     Fritz
    -0.08
    月份
    -0.08
    /linux
    -0.08
    老师
    -0.08
     flooding
    -0.07
    老師
    -0.07
     CMOS
    -0.07
     Slov
    -0.07
     Gilbert
    -0.07
    POSITIVE LOGITS
     residential
    0.11
    Residential
    0.11
    住宅
    0.10
     nightlife
    0.10
     размест
    0.10
     commerces
    0.10
     residencial
    0.09
     मिश्र
    0.09
    층
    0.09
     недвижимости
    0.09
    Act Density 0.012%

    No Known Activations