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

    Neuronpedia

    INDEX
    Explanations

    Condo/Condominium

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    How
    -0.07
    (link
    -0.06
    searchModel
    -0.06
     tòa
    -0.06
     humming
    -0.06
     \|
    -0.06
     wars
    -0.06
    antasy
    -0.06
     year
    -0.06
     virtue
    -0.06
    POSITIVE LOGITS
     mét
    0.08
    ='%
    0.07
    SMART
    0.06
    搜
    0.06
    +w
    0.06
    AVAILABLE
    0.06
    IgnoreCase
    0.06
    фі
    0.06
     nast
    0.06
     Solar
    0.06
    Act Density 0.015%

    No Known Activations