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

    Neuronpedia

    INDEX
    Explanations

    cities and towns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    customers
    -0.07
    /";↵
    -0.06
    SuppressWarnings
    -0.06
     kaufen
    -0.06
    NEWS
    -0.06
    Localization
    -0.06
    される
    -0.06
    apro
    -0.06
    atern
    -0.06
    include
    -0.06
    POSITIVE LOGITS
     messing
    0.07
    577
    0.07
     nerv
    0.07
    [href
    0.07
     ide
    0.06
     společnosti
    0.06
    $status
    0.06
     aplicación
    0.06
     Lottery
    0.06
    &w
    0.06
    Act Density 0.057%

    No Known Activations