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

    Neuronpedia

    INDEX
    Explanations

    net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     builder
    -0.07
     Cats
    -0.07
    olumbia
    -0.06
    "L
    -0.06
    =============↵
    -0.06
    \Resource
    -0.06
    .Cookies
    -0.06
    UFFIX
    -0.06
     beef
    -0.06
     ایجاد
    -0.06
    POSITIVE LOGITS
    (open
    0.08
    NSNotificationCenter
    0.06
    он
    0.06
    онах
    0.06
    .setDescription
    0.06
    ,True
    0.06
    assertTrue
    0.06
     真
    0.06
    -posts
    0.06
    真
    0.06
    Act Density 0.003%

    No Known Activations