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

    Neuronpedia

    INDEX
    Explanations

    escalators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    信息服务
    -0.07
    趣
    -0.07
    晒
    -0.07
    utes
    -0.06
     Gems
    -0.06
    hz
    -0.06
    귁
    -0.06
    hic
    -0.06
     mük
    -0.06
    _vendor
    -0.06
    POSITIVE LOGITS
     offsetY
    0.07
     Optical
    0.07
     refugee
    0.06
    .deep
    0.06
    angi
    0.06
     Dise
    0.06
     זה
    0.06
     maxY
    0.06
    ARRY
    0.06
    ⇓
    0.06
    Act Density 0.001%

    No Known Activations