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

    Neuronpedia

    INDEX
    Explanations

    Language diversity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    当之
    -0.07
    Jean
    -0.07
    ㅡ
    -0.07
     litres
    -0.06
     hơi
    -0.06
     Александр
    -0.06
    上门
    -0.06
     adulte
    -0.06
    ,default
    -0.06
     John
    -0.06
    POSITIVE LOGITS
    куп
    0.07
    舣
    0.07
    Tabs
    0.07
    list
    0.07
     materials
    0.07
    🏰
    0.07
    络
    0.07
    Syn
    0.07
    tre
    0.07
    ню
    0.07
    Act Density 0.258%

    No Known Activations