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

    Neuronpedia

    INDEX
    Explanations

    epidemiology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eature
    -0.07
    ORB
    -0.06
     Raymond
    -0.06
    몬
    -0.06
    ولو
    -0.06
    nev
    -0.06
     "?"
    -0.06
    cock
    -0.06
    ательных
    -0.06
    conti
    -0.06
    POSITIVE LOGITS
    ({↵↵
    0.07
     Alerts
    0.07
     authorize
    0.07
     senate
    0.07
    .p
    0.06
     apro
    0.06
    (AP
    0.06
     Aqu
    0.06
    %");↵
    0.06
     liste
    0.06
    Act Density 0.037%

    No Known Activations