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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đột
    -0.06
    (slug
    -0.06
    ssid
    -0.06
     gren
    -0.06
     отри
    -0.06
     pNode
    -0.06
    esidir
    -0.06
     belki
    -0.06
     disp
    -0.06
     submarine
    -0.06
    POSITIVE LOGITS
    .Now
    0.07
     Strong
    0.06
     BuzzFeed
    0.06
    ΟΛΟΓ
    0.06
    .Our
    0.06
     cháy
    0.06
    updated
    0.06
     enhances
    0.06
     Sidebar
    0.06
    .Logger
    0.06
    Act Density 0.011%

    No Known Activations