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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     A
    -0.07
    YTE
    -0.07
    Vec
    -0.06
    UDGE
    -0.06
    etary
    -0.06
    	get
    -0.06
    ạnh
    -0.06
    랜드
    -0.06
    ώς
    -0.06
    ARS
    -0.06
    POSITIVE LOGITS
    ใน
    0.07
    min
    0.07
    .in
    0.07
    "in
    0.07
     Gmail
    0.07
    pending
    0.07
    mark
    0.06
    ์ใน
    0.06
     материалов
    0.06
     omin
    0.06
    Act Density 0.042%

    No Known Activations