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

    Neuronpedia

    INDEX
    Explanations

    Percentiles and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flourish
    -0.06
     delights
    -0.06
     surplus
    -0.06
     definition
    -0.06
    一次次
    -0.06
     eleg
    -0.06
    젛
    -0.06
    captcha
    -0.06
    艰辛
    -0.06
    clared
    -0.06
    POSITIVE LOGITS
    引入
    0.07
     uncle
    0.07
    /story
    0.07
    _BUCKET
    0.06
    -chart
    0.06
    置于
    0.06
     Within
    0.06
    .Q
    0.06
    .firebaseapp
    0.06
    頭
    0.06
    Act Density 0.024%

    No Known Activations