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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    软件
    -0.07
    学生
    -0.07
     明
    -0.06
    unched
    -0.06
     Viol
    -0.06
     stead
    -0.06
    elters
    -0.06
     scopes
    -0.06
    "].
    -0.06
    utor
    -0.06
    POSITIVE LOGITS
    렇
    0.07
    ()));
    0.07
    _;↵
    0.07
     Yellowstone
    0.06
    чень
    0.06
    θυ
    0.06
    .subplots
    0.06
     Spart
    0.06
     Ebola
    0.06
    「
    0.06
    Act Density 0.070%

    No Known Activations