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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    THON
    -0.07
    于一体
    -0.07
     güne
    -0.06
     endPoint
    -0.06
    مد
    -0.06
     عبد
    -0.06
    -Th
    -0.06
     TableName
    -0.06
     jerseys
    -0.06
     everyone
    -0.06
    POSITIVE LOGITS
    _PA
    0.07
     TSA
    0.07
    也會
    0.07
    必須
    0.07
    луч
    0.07
    ekte
    0.06
     protr
    0.06
    _keyword
    0.06
    粗
    0.06
    Professional
    0.06
    Act Density 0.005%

    No Known Activations