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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kid
    -0.07
     będzie
    -0.07
    .gradient
    -0.07
     backgroundImage
    -0.06
    .abspath
    -0.06
    mojom
    -0.06
    NSBundle
    -0.06
     sockfd
    -0.06
    _PLAYER
    -0.06
    ceb
    -0.06
    POSITIVE LOGITS
     Government
    0.07
     giác
    0.07
     黄
    0.07
     disguise
    0.06
    頁
    0.06
     education
    0.06
     Developing
    0.06
    PERSON
    0.06
     Calendar
    0.06
     Claude
    0.06
    Act Density 0.005%

    No Known Activations