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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ims
    -0.07
    经营模式
    -0.07
     Crunch
    -0.07
    给我
    -0.07
    rong
    -0.06
     ze
    -0.06
    ittel
    -0.06
    .setTimeout
    -0.06
    AMS
    -0.06
    ox
    -0.06
    POSITIVE LOGITS
     numberWith
    0.07
     misog
    0.07
     getName
    0.07
    オスス
    0.07
     htons
    0.07
    花瓣
    0.07
     exclusively
    0.07
    𝗯
    0.07
    Builders
    0.07
    <Scalars
    0.07
    Act Density 0.089%

    No Known Activations