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

    Neuronpedia

    INDEX
    Explanations

    programming and data representation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ав
    -0.08
    表态
    -0.07
    房貸
    -0.07
    LoggedIn
    -0.07
     jsonString
    -0.07
     gunfire
    -0.07
     imperson
    -0.07
    .orders
    -0.07
    瘋
    -0.07
     Prov
    -0.07
    POSITIVE LOGITS
     )↵
    0.07
    앚
    0.07
     Zelda
    0.07
    ,x
    0.07
     gleich
    0.07
    -way
    0.07
    ง
    0.07
    widget
    0.07
     Analyzer
    0.07
    ಌ
    0.06
    Act Density 0.003%

    No Known Activations