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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    深加工
    -0.08
    =read
    -0.07
     알고
    -0.07
     leicht
    -0.07
     البط
    -0.07
    paragus
    -0.07
     ح
    -0.07
    诗人
    -0.07
    红军
    -0.07
     imp
    -0.07
    POSITIVE LOGITS
    掸
    0.07
     Shape
    0.06
    榍
    0.06
     Swarm
    0.06
    猊
    0.06
    局面
    0.06
    _IA
    0.06
    toHaveBeenCalledTimes
    0.06
    ENSOR
    0.06
     ):↵
    0.06
    Act Density 0.022%

    No Known Activations