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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     natural
    -0.07
    mt
    -0.07
    t
    -0.06
    natural
    -0.06
     asoci
    -0.06
    unted
    -0.06
    .buttons
    -0.06
    面积
    -0.06
     industry
    -0.06
    ULSE
    -0.06
    POSITIVE LOGITS
    .App
    0.08
     "}↵
    0.07
     '}↵
    0.07
     şer
    0.06
     datas
    0.06
     handshake
    0.06
     ω
    0.06
    mary
    0.06
     розпов
    0.06
     Howell
    0.06
    Act Density 0.004%

    No Known Activations