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

    Neuronpedia

    INDEX
    Explanations

    身份

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kirch
    -0.09
     Ty
    -0.08
    染
    -0.08
     ಪರಿಸ
    -0.08
    Dv
    -0.07
    ترین
    -0.07
     वातावरण
    -0.07
     laughs
    -0.07
    zell
    -0.07
     tempér
    -0.07
    POSITIVE LOGITS
     conversational
    0.08
     narrator
    0.08
     facilitating
    0.07
     ymlaen
    0.07
     Facilit
    0.07
     собственности
    0.07
    wem
    0.07
    implements
    0.07
     autora
    0.07
     принадлеж
    0.07
    Act Density 0.001%

    No Known Activations