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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     difficulties
    -0.07
     unrest
    -0.06
    designation
    -0.06
    羊毛
    -0.06
     som
    -0.06
     Highest
    -0.06
    Freedom
    -0.06
     נותן
    -0.06
    拉萨
    -0.06
     capacity
    -0.06
    POSITIVE LOGITS
    _CHAT
    0.08
    .endDate
    0.07
    ynet
    0.07
    .playlist
    0.07
     SETUP
    0.07
    加载
    0.07
     Final
    0.07
    .Publish
    0.07
    核
    0.07
    `}
    0.07
    Act Density 0.238%

    No Known Activations