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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    解读
    -0.07
    Renderer
    -0.07
    审查
    -0.07
     Specification
    -0.07
    Filter
    -0.07
    而现在
    -0.07
    意味
    -0.07
    aar
    -0.07
    .getStatusCode
    -0.07
    走入
    -0.07
    POSITIVE LOGITS
     الرياض
    0.08
    teborg
    0.08
     Wichita
    0.07
    (est
    0.07
    剁
    0.07
     Mountain
    0.07
     América
    0.06
    .Mvc
    0.06
     hometown
    0.06
    돨
    0.06
    Act Density 0.106%

    No Known Activations